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 2022/12/13 07:04:51 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@ec9fcc0dac9c09dcb5ef2c56f016c8433c978db6)
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 1e340010d0 deploying docs (apache/tvm@ec9fcc0dac9c09dcb5ef2c56f016c8433c978db6)
1e340010d0 is described below
commit 1e340010d03619bd228fe344c91eb3d31d7b705c
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Dec 13 07:04:44 2022 +0000
deploying docs (apache/tvm@ec9fcc0dac9c09dcb5ef2c56f016c8433c978db6)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 331892 -> 332113 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23825 -> 23380 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.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_adreno.rst.txt | 2 +-
.../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 | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2501 +++++++-------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 35 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 81 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../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 | 14 +-
.../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 | 4 +-
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 | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.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 | 13 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 47 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../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 | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2501 +++++++-------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 35 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 81 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 6 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../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 | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
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 | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 270 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
130 files changed, 2674 insertions(+), 4192 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9ba43750df..0fd9c0ef04 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index d025dae545..2b4fe4d842 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
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 5d448bd836..17b58f5248 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.402 seconds)
+ **Total running time of the script:** ( 1 minutes 11.496 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 74b731c412..6893b377f9 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 970ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 951ms/step
Keras top-1 id: 285, class name: Egyptian cat
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 bb8c7bf8c2..2c068dc8f5 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.zip231a0f9c-1977-4451-8609-6399caf2357d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip86a50036-9ffc-4522-a782-0caaa813b034 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 43fd61c8b3..ed4da253cd 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ 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]
15%|#5 | 6.33M/41.5M [00:00<00:00, 47.6MB/s]
26%|##6 | 10.9M/41.5M [00:00<00:00, 38.2MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 37.7MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 42.8MB/s]
71%|####### | 29.4M/41.5M [00:00<00:00, 51.8MB/s]
83%|########3 | 34.5M/41.5M [00:00<00:00, 49.6MB/s]
95%|#########5| 39.4M/41.5M [00:00<00:00, 47.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 45.4MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 69.8MB/s]
35%|###5 | 14.7M/41.5M [00:00<00:00, 39.1MB/s]
46%|####5 | 19.0M/41.5M [00:00<00:00, 39.4MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 36.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 49.4MB/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 8e864ee4e5..b037a273e1 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
18%|#7 | 7.99M/44.7M [00:00<00:00, 65.3MB/s]
32%|###1 | 14.2M/44.7M [00:00<00:00, 64.2MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 63.7MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 66.3MB/s]
94%|#########4| 42.2M/44.7M [00:00<00:00, 78.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 67.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 71.1MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 60.6MB/s]
49%|####8 | 21.9M/44.7M [00:00<00:00, 47.5MB/s]
60%|#####9 | 26.6M/44.7M [00:00<00:00, 47.0MB/s]
86%|########5 | 38.3M/44.7M [00:00<00:00, 62.1MB/s]
99%|#########9| 44.3M/44.7M [00:00<00:00, 57.0MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 56.5MB/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 e382b22207..fa0a740041 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 14.749 seconds)
+ **Total running time of the script:** ( 1 minutes 13.766 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 8124e98b24..d01ac978d5 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
=================
-**05:55.358** total execution time for **how_to_compile_models** files:
+**05:48.493** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:14.749 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.766 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:12.402 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.496 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:48.612 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.035 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.772 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.595 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.880 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.851 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.270 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.677 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.820 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.982 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.721 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.109 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.635 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.546 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.497 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.435 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 2088bbf2cc..6c028d45b5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2689.8227 2689.9715 2693.9698 2687.3108 1.8960
+ 2755.3861 2754.6390 2763.2280 2752.4093 2.8602
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 92bc4fb07e..789a8f6441 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
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1358 16.1702 16.2391 15.9906 0.0918
+ 16.9692 17.1610 17.4913 16.2506 0.4278
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 a3c6c94949..c013fb9cb4 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
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
5%|4 | 8.10M/170M [00:00<00:01, 84.9MB/s]
10%|9 | 16.2M/170M [00:00<00:02, 70.6MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 56.8MB/s]
18%|#7 | 29.7M/170M [00:00<00:02, 56.2MB/s]
21%|## | 35.3M/170M [00:00<00:02, 56.7MB/s]
25%|##4 | 41.7M/170M [00:00<00:02, 59.8MB/s]
28%|##7 | 47.5M/170M [00:00<00:02, 43.5MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 48.5MB/s]
38%|###7 | 64.1M/170M [00:01<00:02, 55.2MB/s]
44%|####3 | 74.1M/170M [00:01<00:01, 59.5MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 61.1MB/s]
54%|#####4 | 92.3M/170M [00:01<00:01, 61.0MB/s]
58%|#####7 | 98.2M/170M [00:01<00:01, 57.8MB/s]
64%|######3 | 108M/170M [00:01<00:00, 68.9MB/s]
68%|######7 | 115M/170M [00:02<00:00, 66.9MB/s]
72%|#######1 | 122M/170M [00:02<00:00, 54.6MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 72.3MB/s]
84%|########3 | 142M/170M [00:02<00:00, 61.6MB/s]
88%|########7 | 149M/170M [00:02<00:00, 64.1MB/s]
92%|#########1| 156M/170M [00:02<00:00, 56.9MB/s]
95%|#########5| 162M/170M [00:02<00:00, 52.0MB/s]
100%|##########| 170M/170M [00:03<00:00, 59.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 8.40M/170M [00:00<00:01, 88.1MB/s]
10%|# | 17.6M/170M [00:00<00:01, 93.2MB/s]
16%|#5 | 26.5M/170M [00:00<00:01, 84.9MB/s]
20%|## | 34.7M/170M [00:00<00:01, 71.7MB/s]
25%|##4 | 41.8M/170M [00:00<00:01, 71.9MB/s]
29%|##8 | 48.8M/170M [00:00<00:01, 66.3MB/s]
33%|###2 | 56.0M/170M [00:00<00:02, 57.7MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 55.3MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 60.6MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 62.5MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 64.6MB/s]
56%|#####6 | 95.2M/170M [00:01<00:01, 67.5MB/s]
60%|###### | 102M/170M [00:01<00:01, 63.0MB/s]
64%|######3 | 108M/170M [00:01<00:01, 59.5MB/s]
68%|######7 | 115M/170M [00:01<00:00, 63.1MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 60.0MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 57.5MB/s]
80%|######## | 136M/170M [00:02<00:00, 63.8MB/s]
85%|########4 | 144M/170M [00:02<00:00, 62.2MB/s]
89%|########9 | 152M/170M [00:02<00:00, 59.1MB/s]
93%|#########3| 158M/170M [00:02<00:00, 42.6MB/s]
96%|#########6| 163M/170M [00:02<00:00, 44.7MB/s]
100%|##########| 170M/170M [00:02<00:00, 59.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 23.911 seconds)
+ **Total running time of the script:** ( 3 minutes 18.813 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 62b7978f7d..4401f6449e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 51.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 62.9MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 45.3MB/s]
91%|######### | 12.3M/13.6M [00:00<00:00, 38.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 42.4MB/s]
@@ -418,7 +418,7 @@ 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)
- 90.3869 90.3108 94.4654 90.0747 0.4667
+ 90.2464 90.1844 92.1511 90.0543 0.2457
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.252 seconds)
+ **Total running time of the script:** ( 1 minutes 7.083 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 2fafd0c9dc..dcb3fad300 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
@@ -432,7 +432,7 @@ 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)
- 121.0984 121.0770 123.1015 119.7451 0.5446
+ 119.8828 119.7762 124.2719 118.7478 0.8241
@@ -469,7 +469,7 @@ 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 23.556 seconds)
+ **Total running time of the script:** ( 2 minutes 34.268 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 912543e6a8..6e48167317 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.902 seconds)
+ **Total running time of the script:** ( 1 minutes 38.224 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 c241ffe9fe..47002aa088 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
@@ -166,7 +166,7 @@ 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]
2%|2 | 2757/132723 [00:00<00:04, 27566.94KB/s]
5%|5 | 6865/132723 [00:00<00:03, 35513.81KB/s]
9%|8 | 11667/132723 [00:00<00:02, 41222.74KB/s]
15%|#5 | 20195/132723 [00:00<00:01, 58612.17KB/s]
22%|##1 | 28748/132723 [00:00<00:01, 68314.69KB/s]
28%|##8 | 37272/132723 [00:00<00:01, 74065.28KB/s]
35%|###4 | 45886/132723 [00:00<00:01, 78008.04KB/s]
41%|####1 | 54558/132723 [00:00<00:00, 80774.71KB/s]
48%|####7 | 63204/132723 [00:00<00:00, 82549.37KB/s]
54%|#####4 | 71876/132723 [00:01<00:00, 83833.36KB/s]
61%|###### | 80505/132723 [00:01<00:00, 84581.53KB/s]
67%|######7 | 89029/132723 [00:01<00:00, 84779.63KB/s]
74%|#######3 | 97685/132723 [00:01<00:00, 85315.50KB/s]
80%|######## | 106308/132723 [00:01<00:00, 85590.12KB/s]
87%|########6 | 115023/132723 [00:01<00:00, 86057.46KB/s]
93%|#########3
| 123629/132723 [00:01<00:00, 86019.30KB/s]
100%|#########9| 132384/132723 [00:01<00:00, 86477.58KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77774.05KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6604/132723 [00:00<00:01, 66035.97KB/s]
11%|# | 14545/132723 [00:00<00:01, 73892.63KB/s]
17%|#6 | 22516/132723 [00:00<00:01, 76547.18KB/s]
23%|##2 | 30511/132723 [00:00<00:01, 77888.98KB/s]
29%|##9 | 38490/132723 [00:00<00:01, 78571.79KB/s]
35%|###4 | 46435/132723 [00:00<00:01, 78868.02KB/s]
41%|####1 | 54427/132723 [00:00<00:00, 79209.47KB/s]
47%|####6 | 62348/132723 [00:00<00:00, 79086.80KB/s]
53%|#####3 | 70347/132723 [00:00<00:00, 79361.18KB/s]
59%|#####9 | 78323/132723 [00:01<00:00, 79479.90KB/s]
65%|######5 | 86372/132723 [00:01<00:00, 79786.61KB/s]
71%|#######1 | 94433/132723 [00:01<00:00, 80034.04KB/s]
77%|#######7 | 102437/132723 [00:01<00:00, 79620.81KB/s]
83%|########3 | 110438/132723 [00:01<00:00, 79734.68KB/s]
89%|########9 | 118424/132723 [00:01<00:00, 79769.80KB/s]
95%|########
#5| 126413/132723 [00:01<00:00, 79804.73KB/s]
100%|##########| 132723/132723 [00:01<00:00, 78892.40KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 11.804 seconds)
+ **Total running time of the script:** ( 3 minutes 7.759 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 e7b31739de..f66ec53865 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
@@ -5,26 +5,26 @@
Computation times
=================
-**14:01.343** total execution time for **how_to_deploy_models** files:
+**14:08.229** 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``) | 03:23.911 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:18.813 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:11.804 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:07.759 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.556 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:34.268 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:31.902 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:38.224 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.252 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.083 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.286 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:37.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.144 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.046 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.212 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.599 | 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 3ede8dccba..ca80cf9a89 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
@@ -472,7 +472,7 @@ 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.zipd5a3ec28-4834-4b80-834e-ad8d10622d1d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip46fbfc92-cf86-4fcd-98f7-81dde1cd7ada 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 f27f69056d..4986080553 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
=================
-**00:49.954** total execution time for **how_to_extend_tvm** files:
+**00:47.879** 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``) | 00:46.328 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.331 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.487 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.072 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.053 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.009 | 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 17d8f10d87..88d7533f58 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: 7456us [7456us] (46.91%; 46.91%)
- FoldScaleAxis: 8440us [7us] (53.09%; 53.09%)
- FoldConstant: 8433us [1741us] (53.05%; 99.92%)
- InferType: 6692us [6692us] (42.10%; 79.36%)
+ InferType: 7388us [7388us] (46.50%; 46.50%)
+ FoldScaleAxis: 8500us [8us] (53.50%; 53.50%)
+ FoldConstant: 8492us [1691us] (53.45%; 99.90%)
+ InferType: 6801us [6801us] (42.81%; 80.09%)
@@ -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: 6742us [6742us] (44.48%; 44.48%)
- FoldScaleAxis: 8413us [6us] (55.52%; 55.52%)
- FoldConstant: 8408us [1740us] (55.48%; 99.93%)
- InferType: 6668us [6668us] (43.99%; 79.30%)
+ InferType: 6998us [6998us] (45.43%; 45.43%)
+ FoldScaleAxis: 8406us [6us] (54.57%; 54.57%)
+ FoldConstant: 8400us [1730us] (54.53%; 99.93%)
+ InferType: 6671us [6671us] (43.31%; 79.41%)
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 c285ff0a6c..58adfd805f 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: 39.727039 ms
+ Convolution: 35.259742 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 6495bfee00..64be02501a 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
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.348889 ms
+ conv2d with tensor core: 13.357530 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 6f04829e92..dfbab03791 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: 0.019089
- Baseline: 3.294838
+ Numpy running time: 0.018892
+ Baseline: 3.411526
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.326420
+ Opt1: 0.307559
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.351197
+ Opt2: 0.331061
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118419
+ Opt3: 0.116930
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109760
+ Opt4: 0.109341
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110999
+ Opt5: 0.111268
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147183
+ Opt6: 0.146787
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 612e3feec9..9f927bbcb4 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
=================
-**00:35.161** total execution time for **how_to_optimize_operators** files:
+**00:34.957** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.414 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.515 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.502 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.083 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.041 | 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 ff73eea38c..848d8c39fd 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
=================
-**09:05.377** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:58.890** 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``) | 05:37.173 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:32.244 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.140 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.219 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.962 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.982 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.190 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.963 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.401 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.134 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.511 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.349 | 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 008c4e8b60..a7337707d2 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
@@ -239,11 +239,11 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ 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, [1296]), 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" = 112 {
+ 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
@@ -258,830 +258,463 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*18)] = 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_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
+ }
+ 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_3[((((((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_3[((((((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_3[((((((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)
+ }
}
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 1)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 2)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 3)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 4)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 5)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 6)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 7)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 8)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 9)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 10)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 11)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 12)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 13)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 14)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 15)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 16)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 17)] = 0f32
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3248), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3696), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4368), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel_3[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
- }
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1017)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1026)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1017)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1026)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1080)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1089)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1098)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1080)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1089)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1098)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1242)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1242)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 676)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 685)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 676)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 685)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 775)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 775)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 838)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 856)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 865)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 838)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 856)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 865)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 919)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 928)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 937)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 919)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 928)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 937)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1000)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1018)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1027)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1000)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1018)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1027)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1081)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1090)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1081)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1090)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 677)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 686)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 677)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 686)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 776)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 776)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 839)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 857)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 866)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 839)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 857)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 866)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 920)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 929)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 938)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 920)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 929)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 938)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1001)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1019)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1028)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1001)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1019)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1028)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1082)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1091)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1082)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1091)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
+ 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_3: Buffer(kernel_2, float32, [2359296], [])[((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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, 2) {
- for (i2.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((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_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1137,7 +770,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.339 ms
+ Execution time of this operator: 0.348 ms
@@ -1185,22 +818,22 @@ 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=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_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=7)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_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=16)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
@@ -1208,13 +841,13 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_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=7)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_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)
@@ -1234,14 +867,14 @@ 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=112)
+ 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=18)
+ 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=112)
+ 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:
@@ -1259,10 +892,10 @@ 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__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+ __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;
@@ -1277,785 +910,411 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[(((int)threadIdx.x) * 18)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 676)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 685)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 676)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 685)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 775)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 775)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 838)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 856)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 865)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 838)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 856)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 865)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 919)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 928)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 937)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 919)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 928)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 937)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1000)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1018)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1027)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1000)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1018)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1027)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1081)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1090)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1081)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1090)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 677)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 686)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 677)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 686)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 776)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 776)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 839)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 857)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 866)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 839)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 857)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 866)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 920)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 929)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 938)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 920)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 929)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 938)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1001)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1019)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1028)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1001)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1019)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1028)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1082)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1091)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1082)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1091)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
+ 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 < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ 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);
}
}
}
@@ -2118,7 +1377,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 37.173 seconds)
+ **Total running time of the script:** ( 5 minutes 32.244 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 8148a2bb48..b39aaa41bd 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
@@ -643,7 +643,7 @@ 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)
- 7.8974 7.8902 7.9120 7.8899 0.0103
+ 7.8720 7.8716 7.8742 7.8701 0.0017
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.962 seconds)
+ **Total running time of the script:** ( 1 minutes 1.982 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
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 bfe37fe41c..f87d534d9f 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
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.3318 755.2099 758.6138 755.1716 1.6137
+ 752.4773 751.5318 754.6732 751.2268 1.5577
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.140 seconds)
+ **Total running time of the script:** ( 1 minutes 33.219 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 59f531d135..ba7ce89222 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
@@ -386,28 +386,27 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i0.outer: int32, 0, 4) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [1024], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i0.outer*8192) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 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))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32))
compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
@@ -464,7 +463,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.469 ms
+ Execution time of this operator: 1.413 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 e386f08752..2d9d19e662 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:40.780** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.923** 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``) | 00:40.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.887 | 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_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 dce0591685..65181b44a0 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
@@ -387,7 +387,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3071869
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5290336
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -510,7 +510,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1272770
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1600222
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -633,9 +633,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,716168
- No: 4 GFLOPS: 2.13/2.13 result: MeasureResult(costs=(0.10859242999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.3219857215881348, timestamp=1670887231.8734543) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2112981
- No: 5 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6573395
+ No: 4 GFLOPS: 7.15/7.15 result: MeasureResult(costs=(0.032377487,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5499961376190186, timestamp=1670913292.6772933) [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5457353
+ No: 5 GFLOPS: 41.24/41.24 result: MeasureResult(costs=(0.005613020631578947,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.855695724487305, timestamp=1670913300.6602085) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9558310
+ No: 6 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -757,8 +758,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4054950
- No: 6 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7613863
+ No: 7 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -880,8 +881,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6960455
- No: 7 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9165185
+ No: 8 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1003,8 +1004,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2639753
- No: 8 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4906853
+ No: 9 GFLOPS: 1.11/41.24 result: MeasureResult(costs=(0.20899444575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.060100555419922, timestamp=1670913313.511382) [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2779012
+ No: 10 GFLOPS: 36.33/41.24 result: MeasureResult(costs=(0.006371836125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5577633380889893, timestamp=1670913314.2788725) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3491252
+ No: 11 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1126,8 +1129,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2164784
- No: 9 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7640636
+ No: 12 GFLOPS: 2.83/41.24 result: MeasureResult(costs=(0.08171673574999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.836276769638062, timestamp=1670913315.7568543) [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7070502
+ No: 13 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1249,8 +1253,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5529888
- No: 10 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9577906
+ No: 14 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1372,9 +1376,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,472533
- No: 11 GFLOPS: 6.47/6.47 result: MeasureResult(costs=(0.035784664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.670741319656372, timestamp=1670887235.9553034) [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3941797
- No: 12 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5102234
+ No: 15 GFLOPS: 280.31/280.31 result: MeasureResult(costs=(0.0008258900923076922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3507721424102783, timestamp=1670913317.3109255) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,778503
+ No: 16 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1496,8 +1500,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2957511
- No: 13 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2651899
+ No: 17 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1619,8 +1623,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4699800
- No: 14 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3822619
+ No: 18 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1742,9 +1746,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2296000
- No: 15 GFLOPS: 2.27/6.47 result: MeasureResult(costs=(0.10182906325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.269223213195801, timestamp=1670887239.4540393) [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,122874
- No: 16 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9432307
+ No: 19 GFLOPS: 9.68/280.31 result: MeasureResult(costs=(0.023923306666666668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.481926441192627, timestamp=1670913319.0207276) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6355362
+ No: 20 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1866,28 +1870,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8650033
- No: 17 GFLOPS: 0.00/6.47 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
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 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,5074913
- No: 18 GFLOPS: 116.64/116.64 result: MeasureResult(costs=(0.001984684049180328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.62506103515625, timestamp=1670887250.479342) [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,86297
- No: 19 GFLOPS: 4.21/116.64 result: MeasureResult(costs=(0.05497124075,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5942370891571045, timestamp=1670887251.620696) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7011363
- No: 20 GFLOPS: 91.33/116.64 result: MeasureResult(costs=(0.00253465595,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.886324167251587, timestamp=1670887252.3666983) [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3581421
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9964981
@@ -1942,9 +1925,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,86297
+ [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,778503
Finish loading 20 records
- Time cost of this operator: 0.002071
+ Time cost of this operator: 0.001193
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 38f0443f28..3c401e77a8 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 309.3 98.723 (1, 2, 10, 10, 3) 2 1 [309.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.964 (1, 6, 10, 10) 1 1 [3.021]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.981 0.313 (1, 1, 10, 10, 3) 1 1 [0.981]
- Total_time - 313.301 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.9 98.709 (1, 2, 10, 10, 3) 2 1 [311.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.108 0.984 (1, 6, 10, 10) 1 1 [3.108]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.308 (1, 1, 10, 10, 3) 1 1 [0.973]
+ Total_time - 315.981 - - - - -
@@ -397,10 +397,10 @@ 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 138.1 98.106 (1, 6, 10, 10, 1) 2 1 [138.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.817 1.29 (1, 6, 10, 10) 1 1 [1.817]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.85 0.604 (1, 3, 10, 10, 1) 1 1 [0.85]
- Total_time - 140.766 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.9 97.545 (1, 6, 10, 10, 1) 2 1 [104.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.8 1.674 (1, 6, 10, 10) 1 1 [1.8]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.781 (1, 3, 10, 10, 1) 1 1 [0.84]
+ Total_time - 107.54 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 206b516600..ad305a6bb7 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
66%|######5 | 2.25M/3.42M [00:00<00:00, 23.6MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 33.9MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 19.5MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 30.4MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.689 seconds)
+ **Total running time of the script:** ( 1 minutes 4.339 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
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 79bd2564bb..179b70d8ac 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/tmpt02bbwc8/images/random'
+ '/tmp/tmp0wn8glql/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [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], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpt02bbwc8/images/target contains 8144 images
- /tmp/tmpt02bbwc8/images/random contains 5000 images
+ /tmp/tmp0wn8glql/images/target contains 8144 images
+ /tmp/tmp0wn8glql/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2479 - accuracy: 0.9176 - val_loss: 0.2040 - val_accuracy: 0.9335 - 47s/epoch - 145ms/step
+ 328/328 - 47s - loss: 0.2133 - accuracy: 0.9255 - val_loss: 0.1473 - val_accuracy: 0.9475 - 47s/epoch - 145ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.1085 - accuracy: 0.9605 - val_loss: 0.1005 - val_accuracy: 0.9630 - 44s/epoch - 133ms/step
+ 328/328 - 44s - loss: 0.0831 - accuracy: 0.9698 - val_loss: 0.1428 - val_accuracy: 0.9562 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0634 - accuracy: 0.9759 - val_loss: 0.1035 - val_accuracy: 0.9607 - 44s/epoch - 133ms/step
+ 328/328 - 44s - loss: 0.0592 - accuracy: 0.9779 - val_loss: 0.1542 - val_accuracy: 0.9520 - 44s/epoch - 133ms/step
- <keras.callbacks.History object at 0x7ff18f1f8d50>
+ <keras.callbacks.History object at 0x7fe491997b10>
@@ -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 38.062 seconds)
+ **Total running time of the script:** ( 5 minutes 11.592 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 93634b7593..c6f6c812df 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
@@ -5,18 +5,18 @@
Computation times
=================
-**06:48.917** total execution time for **how_to_work_with_microtvm** files:
+**07:20.519** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:38.062 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:11.592 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:05.689 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:04.339 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:53.038 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:52.666 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.155 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.014 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.971 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.906 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 ca36edcfe7..2ee641e30d 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
=================
-**00:45.110** total execution time for **how_to_work_with_relay** files:
+**00:44.578** 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``) | 00:33.059 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.762 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.452 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.261 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.592 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.547 | 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 22f985d89e..c1af76159f 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 0x7ff1903547a0>
+ <function my_cuda_math_rule at 0x7fe434f9d0e0>
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 bc291dba56..deb4ad1f6f 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
=================
-**00:07.197** total execution time for **how_to_work_with_schedules** files:
+**00:08.226** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.626 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.499 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.192 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.352 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.587 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.584 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.561 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.128 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 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_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.023 | 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 65855f38c6..c3a137fdcd 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpsxof8nt0/input0.cc'\nsource_filename = \"/tmp/tmpsxof8nt0/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/tmpspg8davh/input0.cc'\nsource_filename = \"/tmp/tmpspg8davh/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 db332f6b8e..ec5c26b773 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
=================
-**00:27.553** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.742** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.547 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.736 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 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 1d5c8b5794..075cdb6c4b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ 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 30.41s!
+ resnet18_v1 inference graph built in 29.32s!
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 11dc83233d..423b260810 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/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 20.42s!
+ yolov3-tiny inference graph built in 19.96s!
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 3b021cf008..20b0c74ffc 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
=================
-**01:42.691** total execution time for **topic_vta_tutorials_frontend** files:
+**01:41.116** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.347 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.847 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.344 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.268 | 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 e70390ac9d..29da6e5e0b 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
=================
-**00:03.172** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.193** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.700 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.730 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.472 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.463 | 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 b96c63860d..63fc0fecb3 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
=================
-**00:00.829** total execution time for **topic_vta_tutorials** files:
+**00:00.814** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.444 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.435 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.385 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.379 | 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 135b7f9d48..3841977a2b 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -325,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.860 ms
+ Execution time of this operator: 95.602 ms
@@ -443,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 26.916 seconds)
+ **Total running time of the script:** ( 1 minutes 18.995 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 eaf5971516..6d66c64c9d 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 2.07/2.07 result: MeasureResult(costs=(0.1298439702,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.332181930541992, timestamp=1670885776.9059358) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
- No: 2 GFLOPS: 2.72/2.72 result: MeasureResult(costs=(0.0987721906,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.837653398513794, timestamp=1670885779.5298958) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 12.47/12.47 result: MeasureResult(costs=(0.0215343274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5822041034698486, timestamp=1670885780.9209661) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
- No: 4 GFLOPS: 8.73/12.47 result: MeasureResult(costs=(0.030746240599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8782484531402588, timestamp=1670885782.461489) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
- No: 5 GFLOPS: 3.66/12.47 result: MeasureResult(costs=(0.073359286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4101145267486572, timestamp=1670885783.9945142) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
- No: 6 GFLOPS: 2.15/12.47 result: MeasureResult(costs=(0.12476863460000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.222562551498413, timestamp=1670885786.2418654) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
- No: 7 GFLOPS: 12.29/12.47 result: MeasureResult(costs=(0.021848756599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5811359882354736, timestamp=1670885786.8503628) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 8 GFLOPS: 1.60/12.47 result: MeasureResult(costs=(0.1677531396,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.910323143005371, timestamp=1670885789.7896125) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
- No: 9 GFLOPS: 2.18/12.47 result: MeasureResult(costs=(0.1229435804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.196516752243042, timestamp=1670885792.1089928) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
- No: 10 GFLOPS: 13.30/13.30 result: MeasureResult(costs=(0.020176076,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5603663921356201, timestamp=1670885792.6850204) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
+ No: 1 GFLOPS: 10.21/10.21 result: MeasureResult(costs=(0.0262860838,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7390522956848145, timestamp=1670911838.879191) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
+ No: 2 GFLOPS: 9.44/10.21 result: MeasureResult(costs=(0.028445923599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.720085620880127, timestamp=1670911840.3676677) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 3 GFLOPS: 12.29/12.29 result: MeasureResult(costs=(0.0218417912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5817227363586426, timestamp=1670911840.97508) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+ No: 4 GFLOPS: 3.76/12.29 result: MeasureResult(costs=(0.07135844820000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.39719557762146, timestamp=1670911843.1491864) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
+ No: 5 GFLOPS: 2.55/12.29 result: MeasureResult(costs=(0.10535380459999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9290828704833984, timestamp=1670911845.205887) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
+ No: 6 GFLOPS: 1.55/12.29 result: MeasureResult(costs=(0.1733278498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0031306743621826, timestamp=1670911848.2323813) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+ No: 7 GFLOPS: 2.80/12.29 result: MeasureResult(costs=(0.0958068382,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7737319469451904, timestamp=1670911850.789792) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 8 GFLOPS: 0.50/12.29 result: MeasureResult(costs=(0.5358284662,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.813872814178467, timestamp=1670911859.61387) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+ No: 9 GFLOPS: 12.90/12.90 result: MeasureResult(costs=(0.0208089074,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.562669038772583, timestamp=1670911860.3043106) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+ No: 10 GFLOPS: 3.27/12.90 result: MeasureResult(costs=(0.08216418919999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5589423179626465, timestamp=1670911861.8784802) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 1259b1919b..60e5bbcb39 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 519.6813029700003, 'median': 520.3598822499998, 'std': 2.4644942617168786}
+ {'mean': 513.6638269299999, 'median': 513.6743947000014, 'std': 1.8546984959106023}
@@ -554,29 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 14.37/ 17.24 GFLOPS | Progress: (4/20) | 9.09 s
[Task 1/25] Current/Best: 23.57/ 23.57 GFLOPS | Progress: (8/20) | 12.53 s
[Task 1/25] Current/Best: 9.58/ 23.57 GFLOPS | Progress: (12/20) | 16.11 s
[Task 1/25] Current/Best: 12.25/ 23.58 GFLOPS | Progress: (16/20) | 18.71 s
[Task 1/25] Current/Best: 13.18/ 23.58 GFLOPS | Progress: (20/20) | 22.14 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.67/ 18.61 GFLOPS | Progress: (4/20) | 3.61 s
[Task 2/25] Current/Best: 9.53/ 18.61 GFLOPS | Progress: (8/20) | 5.56 s
[Task 2/25] Current/Best: 9.98/ 18.88 GFLOPS | Progress: (12/20) | 7.96 s
[Task 2/25] Current/Best: 17.40/ 18.88 GFLOPS | Progress: (16/20) | 9.38 s
[Task 2/25] Current/Best: 13.89/ 21.18 GFLOPS | Progress: (20/20) | 10.81 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 8.36/ 15.82 GFLOPS | Progress: (4/20) | 4.43 s
[Task 3/25] Current/Best: 4.53/ 17.67 GFLOPS | Progress: (8/20) | 7.11 s
[Task 3/25] Current/Best: 8.58/ 17.67 GFLOPS | Progress: (12/20) | 9.66 s
[Task 3/25] Current/Best: 19.74/ 19.74 GFLOPS | Progress: (16/20) | 12.00 s
[Task 3/25] Current/Best: 11.90/ 23.24 GFLOPS | Progress: (20/20) | 14.26 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 8.61/ 13.55 GFLOPS | Progress: (4/20) | 12.96 s
[Task 4/25] Current/Best: 10.74/ 14.78 GFLOPS | Progress: (8/20) | 24.86 s
[Task 4/25] Current/Best: 13.27/ 16.87 GFLOPS | Progress: (12/20) | 27.47 s
[Task 4/25] Current/Best: 8.06/ 16.87 GFLOPS | Progress: (16/20) | 29.87 s
[Task 4/25] Current/Best: 4.45/ 18.86 GFLOPS | Progress: (20/20) | 32.35 s
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 17.91/ 18.74 GFLOPS | Progress: (4/20) | 3.82 s
[Task 5/25] Current/Best: 11.36/ 18.74 GFLOPS | Progress: (8/20) | 6.44 s
[Task 5/25] Current/Best: 6.78/ 18.74 GFLOPS | Progress: (12/20) | 9.26 s
[Task 5/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (16/20) | 11.06 s
[Task 5/25] Current/Best: 13.07/ 21.23 GFLOPS | Progress: (20/2
0) | 13.71 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.53/ 20.58 GFLOPS | Progress: (4/20) | 3.96 s
[Task 6/25] Current/Best: 13.83/ 20.58 GFLOPS | Progress: (8/20) | 6.90 s
[Task 6/25] Current/Best: 13.03/ 20.58 GFLOPS | Progress: (12/20) | 10.36 s
[Task 6/25] Current/Best: 11.55/ 20.58 GFLOPS | Progress: (16/20) | 15.70 s
[Task 6/25] Current/Best: 10.10/ 20.58 GFLOPS | Progress: (20/20) | 22.58 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 14.27/ 14.27 GFLOPS | Progress: (4/20) | 4.49 s
[Task 7/25] Current/Best: 11.56/ 16.53 GFLOPS | Progress: (8/20) | 6.97 s
[Task 7/25] Current/Best: 14.06/ 16.53 GFLOPS | Progress: (12/20) | 9.18 s
[Task 7/25] Current/Best: 9.45/ 21.73 GFLOPS | Progress: (16/20) | 12.11 s
[Task 7/25] Current/Best: 6.76/ 21.73 GFLOPS | Progress: (20/20) | 15.19 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (4/20) | 5.83 s
[Task 8/25] Current/Best: 3.33/ 21.46 GFLOPS | Progress: (8/20) | 9.22 s
[Task 8/25] Current/Best: 15.70/ 21.46 GFLOPS | Progress: (12/20) | 12.30 s
[Task 8/25] Current/Best: 9.94/ 21.46 GFLOPS | Progress: (16/20) | 16.39 s
[Task 8/25] Current/Best: 6.04/ 21.46 GFLOPS | Progress: (20/20) | 24.98 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 7.13/ 15.00 GFLOPS | Progress: (4/20) | 9.03 s
[Task 9/25] Current/Best: 7.28/ 16.55 GFLOPS | Progress: (8/20) | 20.27 s
[Task 9/25] Current/Best: 7.84/ 16.55 GFLOPS | Progress: (12/20) | 22.58 s
[Task 9/25] Current/Best: 13.88/ 16.55 GFLOPS | Progress: (16/20) | 24.38 s
[Task 9/25] Current/Best: 5.16/ 16.55 GFLOPS | Progress: (20/20) | 29.69 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.53/ 19.09 GFLOPS | Progress: (4/20) | 3.79 s
[Task 10/25] Current/Best: 17.92/ 19.09 GFLOPS | Progress: (8/20) | 5.81 s
[Task 10/25] Current/Best: 9.57/ 19.09 GFLOPS | Progress: (12/20) | 8.18 s
[Task 10/25] Current/Best: 9.01/ 19.09 GFLOPS | Progress: (16/20) | 10.60 s
[Task 10/25] Current/Best: 3.03/ 19.09 GFLOPS | Progress: (20/20) | 12.92 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.18/ 14.02 GFLOPS | Progress: (4/20) | 5.66 s
[Task 11/25] Current/Best: 12.14/ 15.66 GFLOPS | Progress: (8/20) | 8.63 s
[Task 11/25] Current/Best: 14.96/ 15.66 GFLOPS | Progress: (12/20) | 12.07 s
[Task 11/25] Current/Best: 15.62/ 22.13 GFLOPS | Progress: (16/20) | 14.56 s
[Task 11/25] Current/Best: 9.37/ 22.13 GFLOPS | Progress: (20/20) | 17.17 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.01/ 14.67 GFLOPS | Progress: (4/20) | 6.49 s
[Task 12/25] Current/Best: 9.01/ 17.95 GFLOPS | Progress: (8/20) | 9.90 s
[Task 12/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (12/20) | 11.81 s
[Task 12/25] Current/Best: 18.08/ 20.55 GFLOPS | Progress: (16/20) | 16.63 s
[Task 12/25] Current/Best: 3.48/ 20.55 GFLOPS | Progress: (20/20) | 20.38 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (4/20) | 5.15 s
[Task 13/25] Current/Best: 6.13/ 17.78 GFLOPS | Progress: (8/20) | 8.46 s
[Task 13/25] Current/Best: 6.81/ 20.39 GFLOPS | Progress: (12/20) | 11.02 s
[Task 13/25] Current/Best: 7.58/ 20.90 GFLOPS | Progress: (16/20) | 14.43 s
[Task 13/25] Current/Best: 11.79/ 22.91 GFLOPS | Progress: (20/20) | 17.69 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.38/ 20.33 GFLOPS | Progress: (4/20) | 3.17 s
[Task 14/25] Current/Best: 16.83/ 20.33 GFLOPS | Progress: (8/20) | 5.89 s
[Task 14/25] Current/Best: 18.32/ 20.33 GFLOPS | Progress: (12/20) | 8.19 s
[Task 14/25] Current/Best: 6.02/ 20.33 GFLOPS | Progress: (16/20) | 13.58 s
[Task 14/25] Current/Best: 3.00/ 20.33 GFLOPS | Progress: (20/20) | 17.14 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 15/25] Current/Best: 15.81/ 15.81 GFLOPS | Progress: (4/20) | 4.24 s
[Task 15/25] Current/Best: 19.10/ 19.63 GFLOPS | Progress: (8/20) | 6.29 s
[Task 15/25] Current/Best: 8.61/ 21.08 GFLOPS | Progress: (12/20) | 11.02 s
[Task 15/25] Current/Best: 15.65/ 21.08 GFLOPS | Progress: (16/20) | 14.91 s
[Task 15/25] Current/Best: 11.78/ 21.08 GFLOPS | Progress: (20/20) | 18.76 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 15.44/ 16.97 GFLOPS | Progress: (4/20) | 3.46 s
[Task 16/25] Current/Best: 16.65/ 17.96 GFLOPS | Progress: (8/20) | 4.96 s
[Task 16/25] Current/Best: 15.34/ 18.48 GFLOPS | Progress: (12/20) | 6.68 s
[Task 16/25] Current/Best: 15.22/ 18.48 GFLOPS | Progress: (16/20) | 8.63 s
[Task 16/25] Current/Best: 10.84/ 18.48 GFLOPS | Progress: (20/20) | 10.38 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 21.30/ 22.43 GFLOPS | Progress: (4/20) | 4.07 s
[Task 17/25] Current/Best: 19.96/ 22.43 GFLOPS | Progress: (8/20) | 6.67 s
[Task 17/25] Current/Best: 6.18/ 22.43 GFLOPS | Progress: (12/20) | 8.88 s
[Task 17/25] Current/Best: 7.63/ 22.43 GFLOPS | Progress: (16/20) | 12.15 s
[Task 17/25] Current/Best: 11.35/ 22.43 GFLOPS | Progress: (20/20) | 16.44 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.72/ 18.72 GFLOPS | Progress: (4/20) | 4.49 s
[Task 18/25] Current/Best: 9.70/ 18.72 GFLOPS | Progress: (8/20) | 9.47 s
[Task 18/25] Current/Best: 15.50/ 18.72 GFLOPS | Progress: (12/20) | 14.70 s
[Task 18/25] Current/Best: 16.70/ 18.72 GFLOPS | Progress: (16/20) | 21.32 s
[Task 18/25] Current/Best: 14.20/ 18.72 GFLOPS | Progress: (20/20) | 23.55 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.12/ 18.97 GFLOPS | Progress: (4/20) | 4.62 s
[Task 19/25] Current/Best: 1.55/ 21.87 GFLOPS | Progress: (8/20) | 9.45 s
[Task 19/25] Current/Best: 13.92/ 21.87 GFLOPS | Progress: (12/20) | 14.08 s
[Task 19/25] Current/Best: 19.23/ 21.87 GFLOPS | Progress: (16/20) | 18.10 s
[Task 19/25] Current/Best: 17.39/ 21.87 GFLOPS | Progress: (20/20) | 20.36 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 7.92/ 19.31 GFLOPS | Progress: (4/20) | 4.26 s
[Task 20/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (8/20) | 7.94 s
[Task 20/25] Current/Best: 15.13/ 19.66 GFLOPS | Progress: (12/20) | 10.22 s
[Task 20/25] Current/Best: 6.12/ 19.66 GFLOPS | Progress: (16/20) | 13.02 s
[Task 20/25] Current/Best: 7.06/ 19.66 GFLOPS | Progress: (20/20) | 18.02 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 21.31/ 21.31 GFLOPS | Progress: (4/20) | 4.11 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 18.39/ 18.39 GFLOPS | Progress: (4/20) | 7.77 s
[Task 1/25] Current/Best: 9.27/ 18.39 GFLOPS | Progress: (8/20) | 13.21 s
[Task 1/25] Current/Best: 22.06/ 22.06 GFLOPS | Progress: (12/20) | 18.45 s
[Task 1/25] Current/Best: 22.23/ 22.23 GFLOPS | Progress: (16/20) | 22.21 s
[Task 1/25] Current/Best: 9.08/ 22.23 GFLOPS | Progress: (20/20) | 25.18 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.06/ 15.07 GFLOPS | Progress: (4/20) | 3.92 s
[Task 2/25] Current/Best: 5.41/ 16.37 GFLOPS | Progress: (8/20) | 6.12 s
[Task 2/25] Current/Best: 13.51/ 18.11 GFLOPS | Progress: (12/20) | 7.71 s
[Task 2/25] Current/Best: 6.85/ 20.10 GFLOPS | Progress: (16/20) | 9.81 s
[Task 2/25] Current/Best: 12.16/ 20.10 GFLOPS | Progress: (20/20) | 11.45 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.08/ 14.92 GFLOPS | Progress: (4/20) | 4.25 s
[Task 3/25] Current/Best: 18.39/ 18.39 GFLOPS | Progress: (8/20) | 6.60 s
[Task 3/25] Current/Best: 6.01/ 18.39 GFLOPS | Progress: (12/20) | 9.51 s
[Task 3/25] Current/Best: 13.78/ 18.39 GFLOPS | Progress: (16/20) | 12.78 s
[Task 3/25] Current/Best: 16.56/ 18.39 GFLOPS | Progress: (20/20) | 15.35 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 4.73/ 12.34 GFLOPS | Progress: (4/20) | 9.47 s
[Task 4/25] Current/Best: 17.58/ 20.03 GFLOPS | Progress: (8/20) | 14.19 s
[Task 4/25] Current/Best: 5.33/ 20.03 GFLOPS | Progress: (12/20) | 19.16 s
[Task 4/25] Current/Best: 17.96/ 20.03 GFLOPS | Progress: (16/20) | 21.65 s
[Task 4/25] Current/Best: 12.00/ 20.03 GFLOPS | Progress: (20/20) | 23.69 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 3.77/ 17.19 GFLOPS | Progress: (4/20) | 4.05 s
[Task 5/25] Current/Best: 10.04/ 17.19 GFLOPS | Progress: (8/20) | 6.85 s
[Task 5/25] Current/Best: 5.14/ 17.19 GFLOPS | Progress: (12/20) | 10.49 s
[Task 5/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (16/20) | 12.13 s
[Task 5/25] Current/Best: 13.78/ 21.23 GFLOPS | Progress: (20/20) | 14.14 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 15.15/ 19.19 GFLOPS | Progress: (4/20) | 4.11 s
[Task 6/25] Current/Best: 11.47/ 19.19 GFLOPS | Progress: (8/20) | 7.00 s
[Task 6/25] Current/Best: 13.28/ 22.43 GFLOPS | Progress: (12/20) | 9.00 s
[Task 6/25] Current/Best: 9.68/ 22.43 GFLOPS | Progress: (16/20) | 11.34 s
[Task 6/25] Current/Best: 10.85/ 22.43 GFLOPS | Progress: (20/20) | 13.94 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 7.23/ 13.07 GFLOPS | Progress: (4/20) | 4.55 s
[Task 7/25] Current/Best: 15.59/ 15.59 GFLOPS | Progress: (8/20) | 7.39 s
[Task 7/25] Current/Best: 12.36/ 23.47 GFLOPS | Progress: (12/20) | 10.39 s
[Task 7/25] Current/Best: 11.43/ 23.47 GFLOPS | Progress: (16/20) | 12.76 s
[Task 7/25] Current/Best: 5.51/ 23.47 GFLOPS | Progress: (20/20) | 15.07 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.64/ 22.08 GFLOPS | Progress: (4/20) | 8.11 s
[Task 8/25] Current/Best: 10.88/ 22.08 GFLOPS | Progress: (8/20) | 16.22 s
[Task 8/25] Current/Best: 7.98/ 22.08 GFLOPS | Progress: (12/20) | 24.36 s
[Task 8/25] Current/Best: 9.01/ 22.08 GFLOPS | Progress: (16/20) | 30.90 s
[Task 8/25] Current/Best: 12.61/ 22.08 GFLOPS | Progress: (20/20) | 33.49 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.87/ 14.51 GFLOPS | Progress: (4/20) | 5.11 s
[Task 9/25] Current/Best: 5.92/ 18.28 GFLOPS | Progress: (8/20) | 14.96 s
[Task 9/25] Current/Best: 12.08/ 18.28 GFLOPS | Progress: (12/20) | 16.73 s
[Task 9/25] Current/Best: 3.44/ 23.67 GFLOPS | Progress: (16/20) | 18.67 s
[Task 9/25] Current/Best: 9.69/ 23.67 GFLOPS | Progress: (20/20) | 29.45 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 11.02/ 13.53 GFLOPS | Progress: (4/20) | 5.67 s
[Task 10/25] Current/Best: 14.66/ 14.66 GFLOPS | Progress: (8/20) | 7.86 s
[Task 10/25] Current/Best: 12.89/ 14.66 GFLOPS | Progress: (12/20) | 9.84 s
[Task 10/25] Current/Best: 15.60/ 21.17 GFLOPS | Progress: (16/20) | 11.87 s
[Task 10/25] Current/Best: 13.36/ 21.17 GFLOPS | Progress: (20/20
) | 14.77 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 13.34/ 18.03 GFLOPS | Progress: (4/20) | 4.45 s
[Task 11/25] Current/Best: 9.40/ 18.03 GFLOPS | Progress: (8/20) | 8.26 s
[Task 11/25] Current/Best: 6.27/ 18.03 GFLOPS | Progress: (12/20) | 10.79 s
[Task 11/25] Current/Best: 14.21/ 18.03 GFLOPS | Progress: (16/20) | 13.08 s
[Task 11/25] Current/Best: 11.09/ 18.03 GFLOPS | Progress: (20/20) | 16.54 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.55/ 17.90 GFLOPS | Progress: (4/20) | 4.90 s
[Task 12/25] Current/Best: 7.01/ 17.99 GFLOPS | Progress: (8/20) | 7.74 s
[Task 12/25] Current/Best: 10.21/ 17.99 GFLOPS | Progress: (12/20) | 13.22 s
[Task 12/25] Current/Best: 9.11/ 20.47 GFLOPS | Progress: (16/20) | 22.73 s
[Task 12/25] Current/Best: 5.19/ 21.99 GFLOPS | Progress: (20/20) | 25.15 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.53/ 17.82 GFLOPS | Progress: (4/20) | 4.87 s
[Task 13/25] Current/Best: 18.72/ 19.66 GFLOPS | Progress: (8/20) | 8.34 s
[Task 13/25] Current/Best: 18.30/ 19.66 GFLOPS | Progress: (12/20) | 11.85 s
[Task 13/25] Current/Best: 9.59/ 19.66 GFLOPS | Progress: (16/20) | 15.86 s
[Task 13/25] Current/Best: 12.51/ 19.66 GFLOPS | Progress: (20/20) | 17.87 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 6.02/ 16.39 GFLOPS | Progress: (4/20) | 4.84 s
[Task 14/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (8/20) | 6.97 s
[Task 14/25] Current/Best: 13.46/ 18.07 GFLOPS | Progress: (12/20) | 9.74 s
[Task 14/25] Current/Best: 19.91/ 19.91 GFLOPS | Progress: (16/20) | 11.71 s
[Task 14/25] Current/Best: 4.95/ 19.91 GFLOPS | Progress: (20/20) | 19.02 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 11.06/ 16.14 GFLOPS | Progress: (4/20) | 5.81 s
[Task 15/25] Current/Best: 17.73/ 23.18 GFLOPS | Progress: (8/20) | 10.82 s
[Task 15/25] Current/Best: 8.20/ 23.18 GFLOPS | Progress: (12/20) | 12.63 s
[Task 15/25] Current/Best: 19.48/ 23.18 GFLOPS | Progress: (16/20) | 15.64 s
[Task 15/25] Current/Best: 15.86/ 23.18 GFLOPS | Progress: (20/20) | 18.61 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.05/ 14.16 GFLOPS | Progress: (4/20) | 3.60 s
[Task 16/25] Current/Best: 13.48/ 21.39 GFLOPS | Progress: (8/20) | 5.83 s
[Task 16/25] Current/Best: 13.87/ 21.39 GFLOPS | Progress: (12/20) | 7.86 s
[Task 16/25] Current/Best: 18.10/ 21.39 GFLOPS | Progress: (16/20) | 9.98 s
[Task 16/25] Current/Best: 11.07/ 21.39 GFLOPS | Progress: (20/20) | 12.39 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.62/ 19.56 GFLOPS | Progress: (4/20) | 4.77 s
[Task 17/25] Current/Best: 18.56/ 19.56 GFLOPS | Progress: (8/20) | 6.81 s
[Task 17/25] Current/Best: 5.20/ 19.56 GFLOPS | Progress: (12/20) | 10.57 s
[Task 17/25] Current/Best: 20.71/ 20.71 GFLOPS | Progress: (16/20) | 13.24 s
[Task 17/25] Current/Best: 20.17/ 20.71 GFLOPS | Progress: (20/20) | 16.24 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.97/ 18.34 GFLOPS | Progress: (4/20) | 4.61 s
[Task 18/25] Current/Best: 17.29/ 18.34 GFLOPS | Progress: (8/20) | 10.62 s
[Task 18/25] Current/Best: 17.08/ 18.34 GFLOPS | Progress: (12/20) | 12.94 s
[Task 18/25] Current/Best: 12.21/ 19.41 GFLOPS | Progress: (16/20) | 15.90 s
[Task 18/25] Current/Best: 12.68/ 19.41 GFLOPS | Progress: (20/20) | 19.62 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 12.41/ 19.48 GFLOPS | Progress: (4/20) | 5.34 s
[Task 19/25] Current/Best: 10.07/ 19.48 GFLOPS | Progress: (8/20) | 8.01 s
[Task 19/25] Current/Best: 3.08/ 19.48 GFLOPS | Progress: (12/20) | 11.28 s
[Task 19/25] Current/Best: 12.27/ 19.48 GFLOPS | Progress: (16/20) | 13.65 s
[Task 19/25] Current/Best: 7.43/ 21.30 GFLOPS | Progress: (20/20) | 16.89 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 17.60/ 20.94 GFLOPS | Progress: (4/20) | 3.97 s
[Task 20/25] Current/Best: 11.87/ 20.94 GFLOPS | Progress: (8/20) | 6.51 s Done.
+
[Task 20/25] Current/Best: 16.74/ 20.94 GFLOPS | Progress: (12/20) | 9.51 s
[Task 20/25] Current/Best: 4.96/ 20.94 GFLOPS | Progress: (16/20) | 14.74 s
[Task 20/25] Current/Best: 10.50/ 20.94 GFLOPS | Progress: (20/20) | 17.05 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 16.71/ 16.71 GFLOPS | Progress: (4/20) | 6.96 s
[Task 21/25] Current/Best: 1.61/ 21.16 GFLOPS | Progress: (8/20) | 9.39 s
[Task 21/25] Current/Best: 10.30/ 21.16 GFLOPS | Progress: (12/20) | 12.22 s
[Task 21/25] Current/Best: 8.86/ 21.16 GFLOPS | Progress: (16/20) | 16.05 s
[Task 21/25] Current/Best: 17.89/ 21.16 GFLOPS | Progress: (20/20) | 17.74 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 4.14/ 16.29 GFLOPS | Progress: (4/20) | 4.42 s
[Task 22/25] Current/Best: 12.12/ 16.29 GFLOPS | Progress: (8/20
) | 6.46 s
[Task 22/25] Current/Best: 17.98/ 17.98 GFLOPS | Progress: (12/20) | 8.64 s
[Task 22/25] Current/Best: 13.25/ 17.98 GFLOPS | Progress: (16/20) | 13.16 s
[Task 22/25] Current/Best: 20.82/ 20.82 GFLOPS | Progress: (20/20) | 14.76 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 13.14/ 13.14 GFLOPS | Progress: (4/20) | 5.50 s
[Task 23/25] Current/Best: 11.73/ 17.42 GFLOPS | Progress: (8/20) | 8.54 s
[Task 23/25] Current/Best: 22.64/ 22.64 GFLOPS | Progress: (12/20) | 11.16 s
[Task 23/25] Current/Best: 19.83/ 22.64 GFLOPS | Progress: (16/20) | 13.93 s
[Task 23/25] Current/Best: 17.33/ 22.64 GFLOPS | Progress: (20/20) | 16.27 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.78/ 9.11 GFLOPS | Progress: (4/20) | 6.82 s
[Task 24/25] Current/Best: 4.86/ 9.11 GFLOPS | Progress: (8/20) | 17.75 s
[Task 24/25] Current/Best: 3.54/ 10.12 GFLOPS | Progress: (12/20) | 28.67 s
[Task 24/25] Current/Best: 3.14/ 10.12 GFLOPS | Progress: (16/20) | 39.08 s
[Task 24/25] Current/Best: 6.67/ 10.12 GFLOPS | Progress: (20/20) | 50.00 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 21/25] Current/Best: 17.20/ 21.31 GFLOPS | Progress: (8/20) | 6.21 s
[Task 21/25] Current/Best: 11.97/ 21.31 GFLOPS | Progress: (12/20) | 9.19 s
[Task 21/25] Current/Best: 5.15/ 21.31 GFLOPS | Progress: (16/20) | 11.52 s
[Task 21/25] Current/Best: 13.37/ 21.31 GFLOPS | Progress: (20/20) | 13.01 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 12.49/ 19.79 GFLOPS | Progress: (4/20) | 4.89 s
[Task 22/25] Current/Best: 19.50/ 19.79 GFLOPS | Progress: (8/20) | 7.12 s
[Task 22/25] Current/Best: 10.61/ 19.79 GFLOPS | Progress: (12/20) | 9.60 s
[Task 22/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (16/20) | 12.25 s
[Task 22/25] Current/Best: 10.36/ 20.56 GFLOPS | Progress: (20/20) | 14.40 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.83/ 21.92 GFLOPS | Progress: (4/20) | 7.48 s
[Task 23/25] Current/Best: 10.89/ 21.92 GFLOPS | Progress: (8/20) | 10.43 s
[Task 23/25] Current/Best: 21.89/ 21.92 GFLOPS | Progress: (12/20) | 14.78 s
[Task 23/25] Current/Best: 10.28/ 21.92 GFLOPS | Progress: (16/20) | 18.57 s
[Task 23/25] Current/Best: 18.54/ 21.92 GFLOPS | Progress: (20/20) | 21.06 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.44/ 7.11 GFLOPS | Progress: (4/20) | 7.73 s
[Task 24/25] Current/Best: 0.61/ 7.11 GFLOPS | Progress: (8/20) | 18.44 s
[Task 24/25] Current/Best: 1.12/ 8.52 GFLOPS | Progress: (12/20) | 29.40 s
[Task 24/25] Current/Best: 3.34/ 8.52 GFLOPS | Progress: (16/20) | 40.94 s
[Task 24/25] Current/Best: 3.74/ 8.52 GFLOPS | Progress: (20/20) | 52.79 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 8.66/ 8.78 GFLOPS | Progress: (4/20) | 5.72 s
[Task 25/25] Current/Best: 9.02/ 9.02 GFLOPS | Progress: (8/20) | 16.66 s
[Task 25/25] Current/Best: 4.12/ 9.02 GFLOPS | Progress: (12/20) | 28.43 s
[Task 25/25] Current/Best: 8.51/ 9.02 GFLOPS | Progress: (16/20) | 30.69 s
[Task 25/25] Current/Best: 8.19/ 9.02 GFLOPS | Progress: (20/20) | 41.64 s
+ Done.
+
[Task 25/25] Current/Best: 7.96/ 7.96 GFLOPS | Progress: (4/20) | 12.76 s
[Task 25/25] Current/Best: 1.55/ 7.96 GFLOPS | Progress: (8/20) | 24.50 s
[Task 25/25] Current/Best: 2.83/ 8.43 GFLOPS | Progress: (12/20) | 26.92 s
[Task 25/25] Current/Best: 5.28/ 8.43 GFLOPS | Progress: (16/20) | 37.57 s
[Task 25/25] Current/Best: 5.59/ 8.43 GFLOPS | Progress: (20/20) | 40.90 s
@@ -730,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.9228696400014, 'median': 417.5506784000049, 'std': 3.403775726796555}
- unoptimized: {'mean': 519.6813029700003, 'median': 520.3598822499998, 'std': 2.4644942617168786}
+ optimized: {'mean': 424.30159463000336, 'median': 424.43138370001634, 'std': 0.7162677844457208}
+ unoptimized: {'mean': 513.6638269299999, 'median': 513.6743947000014, 'std': 1.8546984959106023}
@@ -754,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 15.783 seconds)
+ **Total running time of the script:** ( 12 minutes 6.177 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 7d7e32aa6a..6984ad72b2 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.261e-07 secs/op
+ 1.243e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index e3267e5012..cb4e44b944 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x21e85570)), stage(b, placeholder(b, 0xc166e90)), 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, 0x2154f520)), stage(b, placeholder(b, 0x269b3cf0)), 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(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 748b993be5..85cd4e3103 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**15:42.285** total execution time for **tutorial** files:
+**15:31.209** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:15.783 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:06.177 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:26.916 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:18.995 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.998 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.720 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.513 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.989 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:22.550 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:27.922 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.492 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.409 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.836 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.819 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.186 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.167 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.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 |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.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 9b72a341bd..a5d36a5506 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
- naive: 0.000007
+ Numpy running time: 0.000008
+ naive: 0.000008
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000007
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.0421500004158584e-06 1.0
- naive 6.6967e-06 0.9509453788409138
- parallel 7.9472e-06 1.1285189891624996
- vector 2.4638299999999998e-05 3.4986900305368445
+ numpy 7.5047099994662856e-06 1.0
+ naive 7.7615e-06 1.0342171783522585
+ parallel 7.4006e-06 0.9861273787429908
+ vector 2.46489e-05 3.2844573610110133
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018775
+ Numpy running time: 0.018520
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.290804
+ none: 3.438327
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.326728
+ blocking: 0.313834
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.352203
+ vectorization: 0.353459
@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, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.117013
+ loop permutation: 0.118149
@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, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108365
+ array packing: 0.107682
@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, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110069
+ block caching: 0.110971
@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, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145883
+ parallelization: 0.146461
@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, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2908042179 1.0
- blocking 0.3267275304 0.0992850102181097
- vectorization 0.35220305760000004 0.10702643921635532
- loop permutation 0.1170133253 0.03555766844576099
- array packing 0.1083648967 0.032929609154674105
- block caching 0.11006863419999999 0.03344733594338207
- parallelization 0.14588306359999997 0.044330520426126736
+ none 3.4383271744 1.0
+ blocking 0.31383369229999997 0.09127511036082976
+ vectorization 0.35345936980000003 0.1027998069618491
+ loop permutation 0.11814898250000001 0.03436234439226029
+ array packing 0.1076817125 0.03131805294788179
+ block caching 0.1109705138 0.03227456497631432
+ parallelization 0.1464610865 0.04259661139593499
@@ -1652,6 +1652,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 1.720 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index c8e64173ed..5914c47d3c 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-51431d5a8c2c0fd956577ea974d0bee4a057e583
+ec9fcc0dac9c09dcb5ef2c56f016c8433c978db6
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 3a61659374..0be4899aca 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ 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 12.402 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.496 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_keras.html b/docs/how_to/compile_models/from_keras.html
index ba765a2ae8..85fad81bbb 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 970ms/step
+1/1 [==============================] - 1s 951ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 445be1eb68..cfa636cb9a 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ 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.zip231a0f9c-1977-4451-8609-6399caf2357d 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.zip86a50036-9ffc-4522-a782-0caaa813b034 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 05e9338d2a..4c22ec1fa8 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,14 +448,12 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<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]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 47.6MB/s]
- 26%|##6 | 10.9M/41.5M [00:00<00:00, 38.2MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 37.7MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 42.8MB/s]
- 71%|####### | 29.4M/41.5M [00:00<00:00, 51.8MB/s]
- 83%|########3 | 34.5M/41.5M [00:00<00:00, 49.6MB/s]
- 95%|#########5| 39.4M/41.5M [00:00<00:00, 47.6MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 45.4MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 69.8MB/s]
+ 35%|###5 | 14.7M/41.5M [00:00<00:00, 39.1MB/s]
+ 46%|####5 | 19.0M/41.5M [00:00<00:00, 39.4MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 36.0MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.7MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 49.4MB/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 33ebd21ea1..3ebd3807af 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,12 +431,13 @@ be unstable.</p>
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]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 65.3MB/s]
- 32%|###1 | 14.2M/44.7M [00:00<00:00, 64.2MB/s]
- 54%|#####3 | 24.0M/44.7M [00:00<00:00, 63.7MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 66.3MB/s]
- 94%|#########4| 42.2M/44.7M [00:00<00:00, 78.6MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 67.3MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 71.1MB/s]
+ 36%|###5 | 16.0M/44.7M [00:00<00:00, 60.6MB/s]
+ 49%|####8 | 21.9M/44.7M [00:00<00:00, 47.5MB/s]
+ 60%|#####9 | 26.6M/44.7M [00:00<00:00, 47.0MB/s]
+ 86%|########5 | 38.3M/44.7M [00:00<00:00, 62.1MB/s]
+ 99%|#########9| 44.3M/44.7M [00:00<00:00, 57.0MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 56.5MB/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 17f6e5654d..23546f27f2 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ 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 14.749 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.766 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 4bdce46fc4..1d0d6f4fa3 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>05:55.358</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:48.493</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</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>01:14.749</p></td>
+<td><p>01:13.766</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>01:12.402</p></td>
+<td><p>01:11.496</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>00:48.612</p></td>
+<td><p>00:47.035</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>00:33.772</p></td>
+<td><p>00:32.595</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>00:29.880</p></td>
+<td><p>00:28.851</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:27.270</p></td>
+<td><p>00:26.677</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:25.820</p></td>
+<td><p>00:25.982</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>00:22.721</p></td>
+<td><p>00:23.109</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>00:17.635</p></td>
+<td><p>00:16.546</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>00:02.497</p></td>
+<td><p>00:02.435</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 64a98e3b7c..bb241af424 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,7 +919,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2689.8227 2689.9715 2693.9698 2687.3108 1.8960
+ 2755.3861 2754.6390 2763.2280 2752.4093 2.8602
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
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 a6e3a45ba1..b613e9917d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1358 16.1702 16.2391 15.9906 0.0918
+ 16.9692 17.1610 17.4913 16.2506 0.4278
</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 c683676510..e4123846e9 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,28 +453,29 @@ be unstable.</p>
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]
- 5%|4 | 8.10M/170M [00:00<00:01, 84.9MB/s]
- 10%|9 | 16.2M/170M [00:00<00:02, 70.6MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:02, 56.8MB/s]
- 18%|#7 | 29.7M/170M [00:00<00:02, 56.2MB/s]
- 21%|## | 35.3M/170M [00:00<00:02, 56.7MB/s]
- 25%|##4 | 41.7M/170M [00:00<00:02, 59.8MB/s]
- 28%|##7 | 47.5M/170M [00:00<00:02, 43.5MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 48.5MB/s]
- 38%|###7 | 64.1M/170M [00:01<00:02, 55.2MB/s]
- 44%|####3 | 74.1M/170M [00:01<00:01, 59.5MB/s]
- 51%|##### | 86.3M/170M [00:01<00:01, 61.1MB/s]
- 54%|#####4 | 92.3M/170M [00:01<00:01, 61.0MB/s]
- 58%|#####7 | 98.2M/170M [00:01<00:01, 57.8MB/s]
- 64%|######3 | 108M/170M [00:01<00:00, 68.9MB/s]
- 68%|######7 | 115M/170M [00:02<00:00, 66.9MB/s]
- 72%|#######1 | 122M/170M [00:02<00:00, 54.6MB/s]
- 79%|#######9 | 134M/170M [00:02<00:00, 72.3MB/s]
- 84%|########3 | 142M/170M [00:02<00:00, 61.6MB/s]
- 88%|########7 | 149M/170M [00:02<00:00, 64.1MB/s]
- 92%|#########1| 156M/170M [00:02<00:00, 56.9MB/s]
- 95%|#########5| 162M/170M [00:02<00:00, 52.0MB/s]
-100%|##########| 170M/170M [00:03<00:00, 59.4MB/s]
+ 5%|4 | 8.40M/170M [00:00<00:01, 88.1MB/s]
+ 10%|# | 17.6M/170M [00:00<00:01, 93.2MB/s]
+ 16%|#5 | 26.5M/170M [00:00<00:01, 84.9MB/s]
+ 20%|## | 34.7M/170M [00:00<00:01, 71.7MB/s]
+ 25%|##4 | 41.8M/170M [00:00<00:01, 71.9MB/s]
+ 29%|##8 | 48.8M/170M [00:00<00:01, 66.3MB/s]
+ 33%|###2 | 56.0M/170M [00:00<00:02, 57.7MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:02, 55.3MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 60.6MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 62.5MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 64.6MB/s]
+ 56%|#####6 | 95.2M/170M [00:01<00:01, 67.5MB/s]
+ 60%|###### | 102M/170M [00:01<00:01, 63.0MB/s]
+ 64%|######3 | 108M/170M [00:01<00:01, 59.5MB/s]
+ 68%|######7 | 115M/170M [00:01<00:00, 63.1MB/s]
+ 72%|#######1 | 122M/170M [00:01<00:00, 60.0MB/s]
+ 75%|#######5 | 128M/170M [00:02<00:00, 57.5MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 63.8MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 62.2MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 59.1MB/s]
+ 93%|#########3| 158M/170M [00:02<00:00, 42.6MB/s]
+ 96%|#########6| 163M/170M [00:02<00:00, 44.7MB/s]
+100%|##########| 170M/170M [00:02<00:00, 59.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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=& [...]
@@ -572,7 +573,7 @@ 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 23.911 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 18.813 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 8045378f7e..1027f9af8c 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,9 @@ training. Other models require a full post training calibration.</p>
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]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 51.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 62.9MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 45.3MB/s]
+ 91%|######### | 12.3M/13.6M [00:00<00:00, 38.5MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 42.4MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +590,7 @@ 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)
- 90.3869 90.3108 94.4654 90.0747 0.4667
+ 90.2464 90.1844 92.1511 90.0543 0.2457
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +629,7 @@ 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 8.252 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.083 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 70c13ae515..9c55fe5fec 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ 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)
- 121.0984 121.0770 123.1015 119.7451 0.5446
+ 119.8828 119.7762 124.2719 118.7478 0.8241
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ 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 23.556 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 34.268 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 f298322e99..6f7fead6f0 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ 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 31.902 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 38.224 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 84acd02de9..5e3cf4de4f 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,24 +462,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 2%|2 | 2757/132723 [00:00<00:04, 27566.94KB/s]
- 5%|5 | 6865/132723 [00:00<00:03, 35513.81KB/s]
- 9%|8 | 11667/132723 [00:00<00:02, 41222.74KB/s]
- 15%|#5 | 20195/132723 [00:00<00:01, 58612.17KB/s]
- 22%|##1 | 28748/132723 [00:00<00:01, 68314.69KB/s]
- 28%|##8 | 37272/132723 [00:00<00:01, 74065.28KB/s]
- 35%|###4 | 45886/132723 [00:00<00:01, 78008.04KB/s]
- 41%|####1 | 54558/132723 [00:00<00:00, 80774.71KB/s]
- 48%|####7 | 63204/132723 [00:00<00:00, 82549.37KB/s]
- 54%|#####4 | 71876/132723 [00:01<00:00, 83833.36KB/s]
- 61%|###### | 80505/132723 [00:01<00:00, 84581.53KB/s]
- 67%|######7 | 89029/132723 [00:01<00:00, 84779.63KB/s]
- 74%|#######3 | 97685/132723 [00:01<00:00, 85315.50KB/s]
- 80%|######## | 106308/132723 [00:01<00:00, 85590.12KB/s]
- 87%|########6 | 115023/132723 [00:01<00:00, 86057.46KB/s]
- 93%|#########3| 123629/132723 [00:01<00:00, 86019.30KB/s]
-100%|#########9| 132384/132723 [00:01<00:00, 86477.58KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 77774.05KB/s]
+ 5%|4 | 6604/132723 [00:00<00:01, 66035.97KB/s]
+ 11%|# | 14545/132723 [00:00<00:01, 73892.63KB/s]
+ 17%|#6 | 22516/132723 [00:00<00:01, 76547.18KB/s]
+ 23%|##2 | 30511/132723 [00:00<00:01, 77888.98KB/s]
+ 29%|##9 | 38490/132723 [00:00<00:01, 78571.79KB/s]
+ 35%|###4 | 46435/132723 [00:00<00:01, 78868.02KB/s]
+ 41%|####1 | 54427/132723 [00:00<00:00, 79209.47KB/s]
+ 47%|####6 | 62348/132723 [00:00<00:00, 79086.80KB/s]
+ 53%|#####3 | 70347/132723 [00:00<00:00, 79361.18KB/s]
+ 59%|#####9 | 78323/132723 [00:01<00:00, 79479.90KB/s]
+ 65%|######5 | 86372/132723 [00:01<00:00, 79786.61KB/s]
+ 71%|#######1 | 94433/132723 [00:01<00:00, 80034.04KB/s]
+ 77%|#######7 | 102437/132723 [00:01<00:00, 79620.81KB/s]
+ 83%|########3 | 110438/132723 [00:01<00:00, 79734.68KB/s]
+ 89%|########9 | 118424/132723 [00:01<00:00, 79769.80KB/s]
+ 95%|#########5| 126413/132723 [00:01<00:00, 79804.73KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 78892.40KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -518,7 +517,7 @@ 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> ( 3 minutes 11.804 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> ( 3 minutes 7.759 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 4dcd474d1b..f7f6d212ec 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>14:01.343</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:08.229</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</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>03:23.911</p></td>
+<td><p>03:18.813</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>03:11.804</p></td>
+<td><p>03:07.759</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>02:23.556</p></td>
+<td><p>02:34.268</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>01:31.902</p></td>
+<td><p>01:38.224</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>01:08.252</p></td>
+<td><p>01:07.083</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:54.117</p></td>
+<td><p>00:54.286</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:37.010</p></td>
+<td><p>00:36.144</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:25.573</p></td>
+<td><p>00:26.046</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:25.212</p></td>
+<td><p>00:25.599</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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 f09d4bbaaf..59ea8b121f 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ 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.zipd5a3ec28-4834-4b80-834e-ad8d10622d1d 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.zip46fbfc92-cf86-4fcd-98f7-81dde1cd7ada 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 237a806fed..d9a4c2f653 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:49.954</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:47.879</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</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>00:46.328</p></td>
+<td><p>00:44.331</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>00:02.546</p></td>
+<td><p>00:02.487</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>00:01.072</p></td>
+<td><p>00:01.053</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>
-<td><p>00:00.007</p></td>
+<td><p>00:00.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 1c14e734f1..d9cc50d897 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ 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: 7456us [7456us] (46.91%; 46.91%)
-FoldScaleAxis: 8440us [7us] (53.09%; 53.09%)
- FoldConstant: 8433us [1741us] (53.05%; 99.92%)
- InferType: 6692us [6692us] (42.10%; 79.36%)
+InferType: 7388us [7388us] (46.50%; 46.50%)
+FoldScaleAxis: 8500us [8us] (53.50%; 53.50%)
+ FoldConstant: 8492us [1691us] (53.45%; 99.90%)
+ InferType: 6801us [6801us] (42.81%; 80.09%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ 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: 6742us [6742us] (44.48%; 44.48%)
-FoldScaleAxis: 8413us [6us] (55.52%; 55.52%)
- FoldConstant: 8408us [1740us] (55.48%; 99.93%)
- InferType: 6668us [6668us] (43.99%; 79.30%)
+InferType: 6998us [6998us] (45.43%; 45.43%)
+FoldScaleAxis: 8406us [6us] (54.57%; 54.57%)
+ FoldConstant: 8400us [1730us] (54.53%; 99.93%)
+ InferType: 6671us [6671us] (43.31%; 79.41%)
</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 5363244160..da8361093f 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ 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: 39.727039 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.259742 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 83de78a445..0c0be595d6 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ 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: 13.348889 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.357530 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 984f9f5cdd..f64b561c53 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ 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: 0.019089
-Baseline: 3.294838
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018892
+Baseline: 3.411526
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ 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: 0.326420
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.307559
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ 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: 0.351197
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.331061
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ 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: 0.118419
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116930
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ 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: 0.109760
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109341
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ 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: 0.110999
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111268
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ 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: 0.147183
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146787
</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 caa55c46ad..d070b678a1 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:35.161</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.957</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</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>00:32.564</p></td>
+<td><p>00:32.414</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>00:01.515</p></td>
+<td><p>00:01.502</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>00:01.083</p></td>
+<td><p>00:01.041</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 3d248ff47f..f83d2e3fbb 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>09:05.377</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:58.890</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</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>05:37.173</p></td>
+<td><p>05:32.244</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>01:33.140</p></td>
+<td><p>01:33.219</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>01:02.962</p></td>
+<td><p>01:01.982</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>00:28.190</p></td>
+<td><p>00:27.963</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:12.401</p></td>
+<td><p>00:12.134</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:11.511</p></td>
+<td><p>00:11.349</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 1f77345064..f8b76b4169 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
@@ -503,11 +503,11 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ 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, [1296]), 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" = 112 {
+ 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
@@ -522,830 +522,463 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*18)] = 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_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.out [...]
+ }
+ 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_3[((((((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)], [...]
+ }
+ 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_3[((((((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)], [...]
+ }
+ 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_3[((((((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)], [...]
+ }
}
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 1)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 2)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 3)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 4)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 5)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 6)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 7)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 8)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 9)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 10)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 11)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 12)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 13)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 14)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 15)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 16)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data_3[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 17)] = 0f32
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3248), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3696), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4368), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel_3[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
- }
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 144)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 153)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 162)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 171)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 180)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 189)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 198)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 207)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 675)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 684)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 702)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 216)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 765)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 774)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 783)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 225)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 90)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 837)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 846)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 864)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 234)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 99)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 927)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 936)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 243)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1017)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1026)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 999)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1017)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1026)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 252)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1080)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1089)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1098)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1080)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1089)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1098)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 261)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 126)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 270)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1242)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 135)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1242)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 279)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 145)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 154)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 163)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 172)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 181)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 190)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 199)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 208)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 676)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 685)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 676)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 685)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 703)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 217)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 775)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 766)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 775)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 226)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 838)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 856)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 865)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 91)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 838)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 856)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 865)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 235)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 919)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 928)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 937)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 100)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 919)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 928)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 937)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 244)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1000)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1018)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1027)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1000)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1018)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1027)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 253)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1081)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1090)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1081)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1090)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 262)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 127)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 271)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 136)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 280)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 146)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 155)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 164)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 173)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 182)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 191)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 200)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 209)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 677)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 686)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 677)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 686)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 704)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 218)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 776)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 767)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 776)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 227)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 839)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 857)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 866)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 92)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 839)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 857)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 866)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 236)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 920)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 929)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 938)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 101)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 920)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 929)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 938)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 245)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1001)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1019)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1028)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1001)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1019)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1028)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 254)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1082)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1091)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1082)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1091)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 263)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 128)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 272)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 137)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*9) + floormod(threadIdx.x, 7)) + 1271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + 281)]))
+ 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_3: Buffer(kernel_2, float32, [2359296], [])[((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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_3[(((((((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_3[((((((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_3[((((((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, 2) {
- for (i2.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((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_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1383,7 +1016,7 @@ 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: 0.339 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.348 ms
</pre></div>
</div>
</div>
@@ -1412,22 +1045,22 @@ 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=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_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=7)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_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=16)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
@@ -1435,13 +1068,13 @@ compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_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=7)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_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)
@@ -1461,14 +1094,14 @@ 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=112)
+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=18)
+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=112)
+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:
@@ -1486,10 +1119,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+ __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;
@@ -1504,785 +1137,411 @@ extern "C" __global__ void __launch_bounds__(112) default_function_ker
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[(((int)threadIdx.x) * 18)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 162)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 171)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 180)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 189)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 198)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 675)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 684)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 702)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 216)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 765)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 774)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 783)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 225)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 90)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 837)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 846)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 864)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 234)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 99)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 927)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 936)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 243)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 999)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1017)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1026)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 252)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1080)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1089)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1098)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 261)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 126)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 270)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 135)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1242)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 279)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 145)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 154)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 163)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 172)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 181)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 190)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 199)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 208)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 676)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 685)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 676)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 685)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 703)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 217)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 775)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 766)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 775)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 226)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 838)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 856)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 865)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 91)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 838)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 856)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 865)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 235)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 919)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 928)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 937)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 100)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 919)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 928)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 937)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 244)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1000)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1018)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1027)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1000)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1018)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1027)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 253)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1081)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1090)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1081)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1090)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 262)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 127)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 271)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 136)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 280)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 146)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 155)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 164)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 173)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 182)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 191)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 200)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 209)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 677)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 686)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 677)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 686)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 704)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 218)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 776)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 767)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 776)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 227)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 839)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 857)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 866)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 92)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 839)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 857)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 866)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 236)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 920)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 929)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 938)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 101)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 920)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 929)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 938)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 245)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1001)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1019)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1028)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1001)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1019)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1028)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 254)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1082)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1091)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1082)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1091)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 263)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 128)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 272)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 137)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 9) + (((int)threadIdx.x) % 7)) + 1271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + 281)]));
+ 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 < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ 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);
}
}
}
@@ -2320,7 +1579,7 @@ 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> ( 5 minutes 37.173 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 32.244 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 404b69de4c..99b3c99d6f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ 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)
- 7.8974 7.8902 7.9120 7.8899 0.0103
+ 7.8720 7.8716 7.8742 7.8701 0.0017
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ 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 2.962 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.982 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_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_network_cuda.py</span></code></a></p>
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 6ffb9c0752..a859205a27 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.3318 755.2099 758.6138 755.1716 1.6137
+ 752.4773 751.5318 754.6732 751.2268 1.5577
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ 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 33.140 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.219 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 df9fe3bcf7..cd0c98f92d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,28 +632,27 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i0.outer: int32, 0, 4) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [1024], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i0.outer*8192) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 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))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32))
compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
@@ -692,7 +691,7 @@ 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: 1.469 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.413 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 7f64c0ace2..5cb8e19ec1 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:40.780</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.923</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</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>00:40.745</p></td>
+<td><p>00:46.887</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>00:00.020</p></td>
+<td><p>00:00.021</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>
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 98a2422a78..d0f5d65df6 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,7 +689,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3071869
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5290336
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -812,7 +812,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1272770
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1600222
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -935,9 +935,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,716168
-No: 4 GFLOPS: 2.13/2.13 result: MeasureResult(costs=(0.10859242999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.3219857215881348, timestamp=1670887231.8734543) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2112981
-No: 5 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6573395
+No: 4 GFLOPS: 7.15/7.15 result: MeasureResult(costs=(0.032377487,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5499961376190186, timestamp=1670913292.6772933) [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5457353
+No: 5 GFLOPS: 41.24/41.24 result: MeasureResult(costs=(0.005613020631578947,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.855695724487305, timestamp=1670913300.6602085) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9558310
+No: 6 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1059,8 +1060,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4054950
-No: 6 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7613863
+No: 7 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1182,8 +1183,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6960455
-No: 7 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9165185
+No: 8 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1305,8 +1306,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2639753
-No: 8 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4906853
+No: 9 GFLOPS: 1.11/41.24 result: MeasureResult(costs=(0.20899444575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.060100555419922, timestamp=1670913313.511382) [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2779012
+No: 10 GFLOPS: 36.33/41.24 result: MeasureResult(costs=(0.006371836125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5577633380889893, timestamp=1670913314.2788725) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3491252
+No: 11 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1428,8 +1431,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2164784
-No: 9 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7640636
+No: 12 GFLOPS: 2.83/41.24 result: MeasureResult(costs=(0.08171673574999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.836276769638062, timestamp=1670913315.7568543) [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7070502
+No: 13 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1551,8 +1555,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5529888
-No: 10 GFLOPS: 0.00/2.13 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9577906
+No: 14 GFLOPS: 0.00/41.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1674,9 +1678,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,472533
-No: 11 GFLOPS: 6.47/6.47 result: MeasureResult(costs=(0.035784664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.670741319656372, timestamp=1670887235.9553034) [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3941797
-No: 12 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5102234
+No: 15 GFLOPS: 280.31/280.31 result: MeasureResult(costs=(0.0008258900923076922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3507721424102783, timestamp=1670913317.3109255) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,778503
+No: 16 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1798,8 +1802,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2957511
-No: 13 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2651899
+No: 17 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1921,8 +1925,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4699800
-No: 14 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3822619
+No: 18 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2044,9 +2048,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2296000
-No: 15 GFLOPS: 2.27/6.47 result: MeasureResult(costs=(0.10182906325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.269223213195801, timestamp=1670887239.4540393) [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,122874
-No: 16 GFLOPS: 0.00/6.47 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9432307
+No: 19 GFLOPS: 9.68/280.31 result: MeasureResult(costs=(0.023923306666666668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.481926441192627, timestamp=1670913319.0207276) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6355362
+No: 20 GFLOPS: 0.00/280.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2168,28 +2172,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8650033
-No: 17 GFLOPS: 0.00/6.47 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
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 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,5074913
-No: 18 GFLOPS: 116.64/116.64 result: MeasureResult(costs=(0.001984684049180328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.62506103515625, timestamp=1670887250.479342) [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,86297
-No: 19 GFLOPS: 4.21/116.64 result: MeasureResult(costs=(0.05497124075,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5942370891571045, timestamp=1670887251.620696) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7011363
-No: 20 GFLOPS: 91.33/116.64 result: MeasureResult(costs=(0.00253465595,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.886324167251587, timestamp=1670887252.3666983) [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3581421
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9964981
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2228,9 +2211,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,86297
+[('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,778503
Finish loading 20 records
-Time cost of this operator: 0.002071
+Time cost of this operator: 0.001193
</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 02cff99f31..9b31b46fba 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -598,10 +598,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.3 98.723 (1, 2, 10, 10, 3) 2 1 [309.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.964 (1, 6, 10, 10) 1 1 [3.021]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.981 0.313 (1, 1, 10, 10, 3) 1 1 [0.981]
-Total_time - 313.301 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.9 98.709 (1, 2, 10, 10, 3) 2 1 [311.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.108 0.984 (1, 6, 10, 10) 1 1 [3.108]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.308 (1, 1, 10, 10, 3) 1 1 [0.973]
+Total_time - 315.981 - - - - -
</pre></div>
</div>
</div>
@@ -653,10 +653,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 138.1 98.106 (1, 6, 10, 10, 1) 2 1 [138.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.817 1.29 (1, 6, 10, 10) 1 1 [1.817]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.85 0.604 (1, 3, 10, 10, 1) 1 1 [0.85]
-Total_time - 140.766 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.9 97.545 (1, 6, 10, 10, 1) 2 1 [104.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.8 1.674 (1, 6, 10, 10) 1 1 [1.8]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.781 (1, 3, 10, 10, 1) 1 1 [0.84]
+Total_time - 107.54 - - - - -
</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_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index cce2234924..0bc89e043f 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,8 +440,8 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 66%|######5 | 2.25M/3.42M [00:00<00:00, 23.6MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 33.9MB/s]
+ 61%|###### | 2.09M/3.42M [00:00<00:00, 19.5MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 30.4MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -565,7 +565,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.689 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.339 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_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">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 1a598f5cc6..6712d5ff78 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ 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/tmpt02bbwc8/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp0wn8glql/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ 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="[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], [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/tmpt02bbwc8/images/target contains 8144 images
-/tmp/tmpt02bbwc8/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], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp0wn8glql/images/target contains 8144 images
+/tmp/tmp0wn8glql/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ 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 - 47s - loss: 0.2479 - accuracy: 0.9176 - val_loss: 0.2040 - val_accuracy: 0.9335 - 47s/epoch - 145ms/step
+328/328 - 47s - loss: 0.2133 - accuracy: 0.9255 - val_loss: 0.1473 - val_accuracy: 0.9475 - 47s/epoch - 145ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.1085 - accuracy: 0.9605 - val_loss: 0.1005 - val_accuracy: 0.9630 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0831 - accuracy: 0.9698 - val_loss: 0.1428 - val_accuracy: 0.9562 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0634 - accuracy: 0.9759 - val_loss: 0.1035 - val_accuracy: 0.9607 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0592 - accuracy: 0.9779 - val_loss: 0.1542 - val_accuracy: 0.9520 - 44s/epoch - 133ms/step
-<keras.callbacks.History object at 0x7ff18f1f8d50>
+<keras.callbacks.History object at 0x7fe491997b10>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ 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 38.062 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 11.592 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 85534b8601..4a7b18a05f 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>06:48.917</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:20.519</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</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>04:38.062</p></td>
+<td><p>05:11.592</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:05.689</p></td>
+<td><p>01:04.339</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:53.038</p></td>
+<td><p>00:52.666</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:08.155</p></td>
+<td><p>00:08.014</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:03.971</p></td>
+<td><p>00:03.906</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></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 6536b594f0..59db610fea 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:45.110</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.578</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</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>00:33.059</p></td>
+<td><p>00:32.762</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>00:10.452</p></td>
+<td><p>00:10.261</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>00:01.592</p></td>
+<td><p>00:01.547</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 6024912476..b2d4507afb 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ 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 0x7ff1903547a0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fe434f9d0e0>
</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 c160f75cab..f16aa4eeed 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:07.197</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.226</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</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>00:04.626</p></td>
+<td><p>00:05.499</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>00:01.192</p></td>
+<td><p>00:01.352</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>00:00.587</p></td>
+<td><p>00:00.584</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>00:00.573</p></td>
+<td><p>00:00.561</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>00:00.115</p></td>
+<td><p>00:00.128</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>
@@ -377,7 +377,7 @@
<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>00:00.024</p></td>
+<td><p>00:00.023</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 93ad65ede9..3791012985 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpsxof8nt0/input0.cc'\nsource_filename = \"/tmp/tmpsxof8nt0/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/tmpspg8davh/input0.cc'\nsource_filename = \"/tmp/tmpspg8davh/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/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 3c870286c9..41364f4684 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ 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>
@@ -1899,7 +1899,7 @@ 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 7ccc6a0c6a..8a1cd47180 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/51431d5a8/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 d24755628c..611c44eeb6 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/51431d5a8/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 27bff8ac81..803f3ccb95 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/51431d5a8/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 7734c00538..5bc6e6d641 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/51431d5a8/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 3f1795e193..e2c45e6b67 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/51431d5a8/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 f456114c3e..91a161ccd4 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/51431d5a8/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 6e721eb80e..15b2d6b1d7 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/51431d5a8/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 b284706aa3..d15ddf4e02 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/51431d5a8/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 85c07b7a79..76d7037a9b 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/51431d5a8/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 2343e7daa7..4b8d54a7b7 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/51431d5a8/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 7edd511087..c9550d49c6 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/51431d5a8/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 ff8be38a8e..e233ba05ee 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/51431d5a8/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 976e6a0c01..1695e45dd1 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/51431d5a8/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 1fca5ab36d..81cc2f2064 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/51431d5a8/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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 070315766f..8908f0358a 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/51431d5a8/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/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/51431d5a8/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index af60d64dd9..f321df85d5 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 48765a8fb0..3c13280728 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 4175958505..8912d2c6ab 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/51431d5a8/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ec9fcc0da/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
... 1521 lines suppressed ...