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 2023/02/07 06:14:01 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@5456fae77655fadf47f61a94e28027c6d39b1e7e)
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 93e7341593 deploying docs (apache/tvm@5456fae77655fadf47f61a94e28027c6d39b1e7e)
93e7341593 is described below
commit 93e7341593e8297bcafd886f7b04170933e7109b
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Feb 7 06:13:53 2023 +0000
deploying docs (apache/tvm@5456fae77655fadf47f61a94e28027c6d39b1e7e)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 309479 -> 336918 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23348 -> 24568 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 | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1989 +++++++++++++++++++-
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 32 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 102 +-
.../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 | 12 +-
.../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 | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
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 | 13 +-
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 | 52 +-
docs/how_to/deploy_models/deploy_prequantized.html | 10 +-
.../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 | 38 +-
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 | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1989 +++++++++++++++++++-
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 32 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 102 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
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 | 12 +-
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 | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 18 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
130 files changed, 4744 insertions(+), 1115 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index e5bb8b4d46..a7d0b269c0 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 3e59e21850..9c19979ef3 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 f9abcd6bb0..669d5956e0 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.704 seconds)
+ **Total running time of the script:** ( 1 minutes 16.673 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 abd25658d0..fcd68c94e2 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ 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 953ms/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 a24c876aea..696db865c2 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip13b06bfd-9422-40ff-8613-9bf21549111d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip0718a6a2-1e6f-48f2-b9e9-fbe575dd14d7 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 7e53f0ee2d..5ed4495b34 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:01, 34.1MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 34.4MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 38.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 46.1MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 36.7MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 38.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 49.5MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 51.0MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 47.3MB/s]
65%|######4 | 26.8M/41.5M [00:00<00:00, 37.6MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.4MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 41.8MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 42.6MB/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 f6acee0968..087a2ab607 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ 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]
14%|#4 | 6.30M/44.7M [00:00<00:00, 44.6MB/s]
24%|##3 | 10.6M/44.7M [00:00<00:01, 26.6MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 34.6MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 42.3MB/s]
63%|######3 | 28.3M/44.7M [00:00<00:00, 38.3MB/s]
72%|#######2 | 32.2M/44.7M [00:00<00:00, 38.5MB/s]
93%|#########3| 41.6M/44.7M [00:01<00:00, 53.4MB/s]
100%|##########| 44.7M/44.7M [00:01<00:00, 42.9MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 62.4MB/s]
41%|#### | 18.2M/44.7M [00:00<00:00, 85.2MB/s]
60%|#####9 | 26.6M/44.7M [00:00<00:00, 70.0MB/s]
89%|########9 | 39.9M/44.7M [00:00<00:00, 92.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 78.6MB/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 98dd7cc400..bf71e0660a 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 24.480 seconds)
+ **Total running time of the script:** ( 1 minutes 21.493 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 557e10230a..6100cfb3fb 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
=================
-**06:31.545** total execution time for **how_to_compile_models** files:
+**06:25.242** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:24.480 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:21.493 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:19.704 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:16.673 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:52.730 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:52.507 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.502 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.958 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.966 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.572 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:30.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:29.987 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.295 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.688 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:25.150 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.254 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.293 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:21.474 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.666 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.635 | 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 c06d6e471c..e4cf9f8df0 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
@@ -727,7 +727,7 @@ 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)
- 2716.2963 2715.5848 2723.3126 2712.9677 3.0337
+ 2754.1907 2753.1235 2760.5896 2750.7188 3.2330
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 9d6b7347ed..e9c2e63dc3 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
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2804 16.3079 16.7753 15.6254 0.4288
+ 15.5475 15.4613 16.2250 15.4136 0.2319
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 ee2f48b545..b45050ff60 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
@@ -130,7 +130,7 @@ 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 | 7.99M/170M [00:00<00:04, 39.5MB/s]
9%|9 | 16.0M/170M [00:00<00:03, 46.3MB/s]
13%|#3 | 22.3M/170M [00:00<00:03, 50.9MB/s]
16%|#6 | 27.4M/170M [00:00<00:03, 49.0MB/s]
19%|#8 | 32.1M/170M [00:00<00:03, 37.2MB/s]
24%|##3 | 40.2M/170M [00:00<00:02, 48.6MB/s]
27%|##7 | 46.3M/170M [00:01<00:02, 43.5MB/s]
30%|### | 51.0M/170M [00:01<00:02, 43.5MB/s]
36%|###5 | 60.7M/170M [00:01<00:01, 57.7MB/s]
39%|###9 | 66.8M/170M [00:01<00:02, 40.3MB/s]
44%|####3 | 74.0M/170M [00:01<00:02, 47.3MB/s]
47%|####6 | 79.7M/170M [00:01<00:01, 49.7MB/s]
50%|##### | 85.2M/170M [00:01<00:01, 50.2MB/s]
53%|#####3 | 90.6M/170M [00:02<00:04, 19.5MB/s]
57%|#####6 | 96.0M/170M [00:02<00:03, 22.4MB/s]
61%|######1 | 104M/170M [00:03<00:02, 27.6MB/s]
66%|######5 | 112M/170M [00:03<00:01, 34.9MB/s
]
71%|####### | 120M/170M [00:03<00:01, 41.3MB/s]
74%|#######4 | 126M/170M [00:03<00:01, 43.5MB/s]
78%|#######7 | 132M/170M [00:03<00:00, 47.6MB/s]
81%|########1 | 138M/170M [00:03<00:00, 37.4MB/s]
86%|########5 | 146M/170M [00:03<00:00, 45.5MB/s]
89%|########9 | 152M/170M [00:03<00:00, 45.5MB/s]
93%|#########3| 158M/170M [00:04<00:00, 49.4MB/s]
96%|#########6| 164M/170M [00:04<00:00, 43.7MB/s]
99%|#########9| 168M/170M [00:04<00:00, 41.3MB/s]
100%|##########| 170M/170M [00:04<00:00, 40.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 60.4MB/s]
8%|8 | 14.3M/170M [00:00<00:03, 42.5MB/s]
11%|# | 18.6M/170M [00:00<00:03, 41.0MB/s]
17%|#6 | 28.3M/170M [00:00<00:02, 59.7MB/s]
20%|## | 34.5M/170M [00:00<00:02, 60.4MB/s]
24%|##3 | 40.7M/170M [00:00<00:02, 61.2MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 60.0MB/s]
33%|###2 | 56.0M/170M [00:01<00:01, 60.3MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 66.0MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 70.4MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 69.0MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 68.4MB/s]
57%|#####6 | 96.8M/170M [00:01<00:01, 74.8MB/s]
61%|######1 | 104M/170M [00:01<00:00, 69.0MB/s]
66%|######5 | 112M/170M [00:01<00:00, 70.9MB/s]
71%|####### | 120M/170M [00:02<00:00, 58.5MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 62.9MB/s]
80%|######## | 136M/170M [00:02<00:00, 65.4MB/s]
85%|########4 | 144M/170M [00:02<00:00, 59.8MB/s]
89%|########9 | 152M/170M [00:02<00:00, 59.8MB/s]
94%|#########4| 160M/170M [00:02<00:00, 64.8MB/s]
99%|#########8| 168M/170M [00:02<00:00, 69.1MB/s]
100%|##########| 170M/170M [00:02<00:00, 64.0MB/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').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 32.347 seconds)
+ **Total running time of the script:** ( 3 minutes 21.372 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 3216434233..1dd3c458f1 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ 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]
38%|###8 | 5.18M/13.6M [00:00<00:00, 32.3MB/s]
61%|###### | 8.26M/13.6M [00:00<00:00, 24.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 33.0MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 44.8MB/s]
91%|######### | 12.3M/13.6M [00:00<00:00, 38.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 42.6MB/s]
@@ -409,7 +409,7 @@ 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)
- 88.8169 88.7828 89.4389 88.6245 0.1510
+ 90.0147 89.9609 90.6130 89.8015 0.1830
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.722 seconds)
+ **Total running time of the script:** ( 1 minutes 12.374 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 35711bd8b4..ac6bf1cb56 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
@@ -423,7 +423,7 @@ 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)
- 117.8774 117.8101 124.2038 116.5215 0.9200
+ 116.7811 116.5945 123.2361 115.7550 0.9130
@@ -460,7 +460,7 @@ 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 25.758 seconds)
+ **Total running time of the script:** ( 2 minutes 25.213 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 05b80f0bb6..cf0ea78600 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 50.887 seconds)
+ **Total running time of the script:** ( 1 minutes 40.396 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 3356bbd4b7..96769d987f 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
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5259/132723 [00:00<00:02, 52583.28KB/s]
10%|9 | 12773/132723 [00:00<00:01, 65846.94KB/s]
15%|#5 | 20367/132723 [00:00<00:01, 70442.11KB/s]
21%|##1 | 27971/132723 [00:00<00:01, 72648.16KB/s]
27%|##6 | 35540/132723 [00:00<00:01, 73738.49KB/s]
33%|###2 | 43156/132723 [00:00<00:01, 74557.36KB/s]
38%|###8 | 50781/132723 [00:00<00:01, 75107.45KB/s]
44%|####3 | 58293/132723 [00:00<00:00, 75108.85KB/s]
50%|####9 | 65825/132723 [00:00<00:00, 75172.35KB/s]
56%|#####5 | 73754/132723 [00:01<00:00, 76442.27KB/s]
61%|######1 | 81572/132723 [00:01<00:00, 76968.58KB/s]
67%|######7 | 89454/132723 [00:01<00:00, 77529.35KB/s]
73%|#######3 | 97445/132723 [00:01<00:00, 78246.59KB/s]
79%|#######9 | 105468/132723 [00:01<00:00, 78844.62KB/s]
85%|########5 | 113468/132723 [00:01<00:00, 79190.49KB/s]
92%|#########
1| 121508/132723 [00:01<00:00, 79551.92KB/s]
98%|#########7| 129572/132723 [00:01<00:00, 79867.83KB/s]
100%|##########| 132723/132723 [00:01<00:00, 76297.77KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6186/132723 [00:00<00:02, 61841.63KB/s]
11%|# | 14142/132723 [00:00<00:01, 72260.84KB/s]
17%|#6 | 22210/132723 [00:00<00:01, 76100.20KB/s]
23%|##2 | 30293/132723 [00:00<00:01, 77964.40KB/s]
29%|##8 | 38229/132723 [00:00<00:01, 78463.74KB/s]
35%|###4 | 46109/132723 [00:00<00:01, 78575.41KB/s]
41%|#### | 54072/132723 [00:00<00:00, 78918.15KB/s]
47%|####6 | 61964/132723 [00:00<00:00, 78763.99KB/s]
53%|#####2 | 69897/132723 [00:00<00:00, 78939.60KB/s]
59%|#####8 | 77792/132723 [00:01<00:00, 77819.03KB/s]
64%|######4 | 85578/132723 [00:01<00:00, 77443.16KB/s]
70%|####### | 93325/132723 [00:01<00:00, 77153.97KB/s]
76%|#######6 | 101043/132723 [00:01<00:00, 77027.61KB/s]
82%|########1 | 108747/132723 [00:01<00:00, 76913.75KB/s]
88%|########7 | 116440/132723 [00:01<00:00, 76587.46KB/s]
94%|########
#3| 124101/132723 [00:01<00:00, 76589.19KB/s]
99%|#########9| 131777/132723 [00:01<00:00, 76637.78KB/s]
100%|##########| 132723/132723 [00:01<00:00, 76994.32KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 38.326 seconds)
+ **Total running time of the script:** ( 3 minutes 38.023 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 16e7366046..c0d4410a5f 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
=================
-**15:11.582** total execution time for **how_to_deploy_models** files:
+**14:45.835** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:38.326 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:38.023 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:32.347 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:21.372 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:25.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:25.213 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:50.887 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:40.396 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:13.722 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:12.374 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.774 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.040 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:40.938 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:39.783 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.173 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.481 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.651 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.145 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 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 3e160beecb..538a8af590 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
@@ -463,7 +463,7 @@ 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.zip81f8bf3f-9b9e-4e3b-8d3a-a7f671a4c416 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf828034c-cedd-4764-bee2-0f27631d164a 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 51a8d4cb05..fb75823bdf 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
=================
-**00:51.732** total execution time for **how_to_extend_tvm** files:
+**00:51.494** 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``) | 00:48.030 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:47.832 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.633 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.613 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.061 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.041 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 3a6eaf6a12..5e85dd528e 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
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 20675us [20675us] (48.67%; 48.67%)
- FoldScaleAxis: 21805us [6us] (51.33%; 51.33%)
- FoldConstant: 21799us [1731us] (51.32%; 99.97%)
- InferType: 20068us [20068us] (47.24%; 92.06%)
+ InferType: 20741us [20741us] (48.76%; 48.76%)
+ FoldScaleAxis: 21795us [6us] (51.24%; 51.24%)
+ FoldConstant: 21789us [1657us] (51.22%; 99.97%)
+ InferType: 20131us [20131us] (47.33%; 92.39%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 20037us [20037us] (48.28%; 48.28%)
- FoldScaleAxis: 21461us [5us] (51.72%; 51.72%)
- FoldConstant: 21456us [1652us] (51.70%; 99.98%)
- InferType: 19804us [19804us] (47.72%; 92.30%)
+ InferType: 20398us [20398us] (48.52%; 48.52%)
+ FoldScaleAxis: 21640us [5us] (51.48%; 51.48%)
+ FoldConstant: 21635us [1645us] (51.47%; 99.98%)
+ InferType: 19990us [19990us] (47.55%; 92.40%)
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 8a36462846..ab93ed86b6 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
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.103969 ms
+ Convolution: 50.872032 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 19b0161ec3..5762da85b8 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
@@ -608,7 +608,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.686000 ms
+ conv2d with tensor core: 7.009689 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 edb4aef84c..3c42a91438 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.017782
- Baseline: 3.359834
+ Numpy running time: 0.017636
+ Baseline: 3.227152
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.299228
+ Opt1: 0.295510
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.328327
+ Opt2: 0.334643
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.113307
+ Opt3: 0.112489
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108601
+ Opt4: 0.108494
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.109748
+ Opt5: 0.110456
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.144683
+ Opt6: 0.146283
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 3f00b1f6fb..41e8206a8a 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
=================
-**00:34.318** total execution time for **how_to_optimize_operators** files:
+**00:34.087** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.769 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.504 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.491 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.512 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.058 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.071 | 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 8206cc889b..5396250855 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
=================
-**09:31.794** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:49.378** 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``) | 05:51.365 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:08.157 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:37.827 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:38.187 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:06.385 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:06.315 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.180 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.735 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.268 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.248 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.769 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.735 | 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 f486e13c3e..de7503a10a 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
@@ -244,57 +244,956 @@ cooperative fetching, unrolling and operator fusion.
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 128)
- conv2d_nchw = T.allocate([4], "float32", "local")
- pad_temp_shared = T.allocate([252], "float32", "shared")
- kernel_shared = T.allocate([48], "float32", "shared")
+ T.launch_thread(blockIdx_x, 64)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([2016], "float32", "shared")
+ kernel_shared = T.allocate([768], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 49)
+ T.launch_thread(threadIdx_x, 28)
conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(128, 3):
- cse_var_2: T.int32 = rc_outer_outer * 196
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer, ry_outer_outer in T.grid(16, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 1568
cse_var_1: T.int32 = ry_outer_outer * 7
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((252,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((2016,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 // 9 + ry_outer_outer and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + cse_var_1 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(1 <= (threadIdx_x_1 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 49) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(1 <= (threadIdx_x_1 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 147) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= (threadIdx_x_1 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- if T.likely(threadIdx_x_1 < 7):
- pad_temp_shared_1[threadIdx_x_1 + 245] = T.if_then_else((threadIdx_x_1 + 56) // 9 + ry_outer_outer < 8 and threadIdx_x_1 < 6, data_1[cse_var_2 + (threadIdx_x_1 + 245) // 9 * 7 + cse_var_1 + threadIdx_x_1 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 56] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 56) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 57] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 57) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 112] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 112) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 113] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 113) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 168] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 168) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 169] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 169) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 224] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 224) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 225] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 167], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 280] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 280) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 281] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 281) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 336] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 336) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 337] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 337) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 392] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 392) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 393] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 393) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 448] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 448) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 449] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 449) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 504] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 384], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 505] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 505) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 560] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 560) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 561] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 561) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 616] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 616) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 617] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 617) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 672] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 672) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 673] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 673) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 728] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 728) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 729] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 559], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 784] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 784) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 785] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 785) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 840] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 840) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 841] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 841) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 896] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 896) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 897] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 897) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 952] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 952) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 953] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 953) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1008] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 776], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1009] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1009) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1064] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1064) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1065] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1065) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1120] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1120) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1121] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1121) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1176) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1177] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1177) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1232] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1232) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1233] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 951], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1288] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1288) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1289] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1289) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1344] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1344) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1345] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1345) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1400] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1400) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1401] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1401) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1456] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1456) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1457] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1457) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1512] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 1168], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1513] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1513) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1568] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1568) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1569] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1569) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1624] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1624) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1625] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1625) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1680] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1680) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1681] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1681) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1736] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1736) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1737] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 1343], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1792] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1792) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1793] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1793) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1848] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1848) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1849] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1849) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1904] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1904) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1905] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1905) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1960] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1960) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1961] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1961) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((48,), data=kernel_shared, scope="shared")
- with T.launch_thread(threadIdx_x_2, 49):
- if T.likely(threadIdx_x_2 < 48):
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
- for rc_outer_inner, rx_outer_inner in T.grid(2, 3):
- cse_var_3: T.int32 = rc_outer_inner * 6 + rx_outer_inner
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 24]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 27]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 36]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 39]
+ kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
+ with T.launch_thread(threadIdx_x_2, 28):
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + threadIdx_x_2 * 64 % 96 // 3 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 1] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 1) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 2] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 2) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 3] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 1) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 4] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 4) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 5] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 5) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 6] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 2) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 7] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 7) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 8] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 8) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 9] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 3) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 10] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 10) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 11] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 11) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 12] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 4) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 13] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 13) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 14] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 14) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 15] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 5) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 16] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 16) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 17] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 17) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 18] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 6) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 19] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 19) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 20] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 20) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 21] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 7) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 22] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 22) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 23] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 23) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 24] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 8) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 25] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 25) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 26] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 26) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 27] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 9) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 28] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 28) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 29] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 29) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 30] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 10) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 31] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 31) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 32] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 32) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 33] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 11) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 34] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 34) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 35] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 35) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 36] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 12) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 37] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 37) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 38] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 38) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 39] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 13) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 40] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 40) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 41] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 41) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 42] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 14) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 43] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 43) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 44] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 44) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 45] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 15) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 46] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 46) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 47] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 47) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 48] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 16) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 49] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 49) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 50] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 50) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 51] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 17) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 52] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 52) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 53] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 53) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 54] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 18) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 55] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 55) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 56] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 56) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 57] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 19) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 58] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 58) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 59] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 59) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 60] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 20) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 61] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 61) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 62] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 62) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 63] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 21) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ for rc_outer_inner in range(2):
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 126] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 189] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 252] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 315] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 378] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 441] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 504] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 567] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 630] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 693] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 756] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 819] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 882] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 945] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 126] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 189] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 252] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 315] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 378] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 441] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 504] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 567] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 630] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 693] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 756] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 819] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 882] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 945] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 71] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 134] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 197] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 260] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 323] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 386] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 449] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 512] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 575] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 638] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 701] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 764] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 827] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 890] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 953] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 71] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 134] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 197] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 260] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 323] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 386] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 449] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 512] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 575] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 638] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 701] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 764] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 827] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 890] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 953] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 4 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x + 98] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 4 + i1_inner + 2], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 1] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 2] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 3] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 4] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 5] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 6] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
@@ -344,7 +1243,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.322 ms
+ Execution time of this operator: 0.298 ms
@@ -394,17 +1293,17 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=1)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
@@ -415,14 +1314,14 @@ 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=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -439,16 +1338,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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)
+ 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=64)
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=49)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=2)
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=49)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
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", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -466,46 +1365,976 @@ 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__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[252];
- __shared__ float kernel_shared[48];
+ extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 49) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 147) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((((((int)threadIdx.x) + 56) / 9) + ry_outer_outer) < 8) && (((int)threadIdx.x) < 6)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 245) / 9) * 7)) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) * 2)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 56)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 57)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 57) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 112)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 113)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 168)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 169)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 169) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 224)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 225)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 167)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 280)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 281)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 281) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 336)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 337)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 392)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 393)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 448)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 449)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 504)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 505)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 505) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 560)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 561)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 561) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 616)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 617)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 617) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 672)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 673)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 673) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 728)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 729)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 559)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 784)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 785)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 840)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 841)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 841) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 896)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 897)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 897) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 952)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 953)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 953) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1008)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 776)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1009)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1009) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1064)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1065)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1065) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1120)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1121)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1121) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1177) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1232)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1233)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 951)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1288)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1289)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1289) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1344)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1345)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1345) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1400)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1401)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1401) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1456)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1457)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1457) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1512)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1513)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1513) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1568)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1569)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1569) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1624)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1625)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1625) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1680)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1681)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1681) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1736)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1737)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 1343)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1792)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1793)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1793) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1848)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1849)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1849) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1904)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1905)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1905) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1960)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1961)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1961) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[(((int)threadIdx.x) * 64)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
}
- if (((int)threadIdx.x) < 48) {
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 1)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 1) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 2)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 2) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 3)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 1) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 4)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 5)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 5) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 6)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 2) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 7)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 7) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 8)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 9)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 3) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 10)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 10) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 11)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 11) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 12)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 13)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 13) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 14)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 14) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 15)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 5) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 16)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 17)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 17) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 18)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 6) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 19)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 19) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 20)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 20) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 21)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 7) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 22)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 22) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 23)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 23) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 24)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 25)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 25) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 26)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 26) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 27)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 9) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 28)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 28) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 29)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 29) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 30)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 10) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 31)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 31) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 32)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 33)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 11) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 34)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 34) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 35)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 35) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 36)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 12) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 37)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 37) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 38)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 38) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 39)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 13) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 40)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 40) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 41)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 41) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 42)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 14) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 43)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 43) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 44)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 44) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 45)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 15) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 46)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 46) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 47)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 47) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 48)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 49) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 50)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 50) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 51)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 17) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 52)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 52) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 53)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 53) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 54)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 18) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 55)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 55) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 56)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 57)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 19) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 58)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 58) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 59)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 59) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 60)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 20) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 61)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 61) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 62)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 62) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 63)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 21) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
}
__syncthreads();
for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 6) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 39)]));
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -567,7 +2396,7 @@ 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 51.365 seconds)
+ **Total running time of the script:** ( 6 minutes 8.157 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 666b13a8dc..5034164af3 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9244 7.9249 7.9365 7.9116 0.0102
+ 7.8829 7.8821 7.8860 7.8805 0.0023
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.385 seconds)
+ **Total running time of the script:** ( 1 minutes 6.315 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 b17af2e0fd..e981cf3a69 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 738.6193 737.4406 742.1454 736.2720 2.5385
+ 750.4639 748.3697 754.7954 748.2266 3.0634
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 37.827 seconds)
+ **Total running time of the script:** ( 1 minutes 38.187 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 6dd6cf06de..2cfdc57c75 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
@@ -389,27 +389,27 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer in T.parallel(8):
- compute_1 = T.allocate([64], "float32", "global")
- for i1_outer in range(128):
- compute_2 = T.Buffer((64,), data=compute_1)
- for i_inner_init, j_init in T.grid(16, 4):
- compute_2[i_inner_init * 4 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i1_outer // 4, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 16, 4):
+ for i0_outer_i1_outer_fused in T.parallel(64):
+ compute_1 = T.allocate([1024], "float32", "global")
+ compute_2 = T.Buffer((1024,), data=compute_1)
+ for i_outer_inner in range(2):
+ for i_inner_init, j_init in T.grid(32, 16):
+ compute_2[i_outer_inner * 512 + i_inner_init * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 32, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 32, 16):
cse_var_1 = T.var("int32")
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_2: T.int32 = i1_outer // 4
+ cse_var_2: T.int32 = i0_outer_i1_outer_fused % 32
if T.likely(elem_idx < placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]):
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- cse_var_3: T.int32 = i_inner * 4 + j
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + i1_outer % 4 * 4 + j] * T.max(placeholder_7[i0_outer * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
- for i0_inner in range(16):
- cse_var_4: T.int32 = i0_outer * 8192 + i0_inner * 512 + i1_outer * 4
- compute_3 = T.Buffer((65536,), data=compute.data)
- placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4:cse_var_4 + 4] = T.max(compute_2[i0_inner * 4:i0_inner * 4 + 4] + placeholder_5[cse_var_4:cse_var_4 + 4], T.Broadcast(T.float32(0), 4))
+ cse_var_3: T.int32 = i_outer_inner * 512 + i_inner * 16 + j
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_outer_inner * 8192 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
+ for i0_inner in range(64):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 32 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ compute_3[cse_var_4:cse_var_4 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_4:cse_var_4 + 16], T.Broadcast(T.float32(0), 16))
@@ -459,7 +459,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.842 ms
+ Execution time of this operator: 1.623 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 4f4c948431..ba92dfef82 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
=================
-**00:52.416** total execution time for **how_to_tune_with_autotvm** files:
+**00:38.135** 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``) | 00:52.384 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:38.101 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 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 adad3da47a..da434a6202 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
@@ -390,9 +390,29 @@ 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, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4412671
- No: 2 GFLOPS: 28.55/28.55 result: MeasureResult(costs=(0.008107613642857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.30165433883667, timestamp=1675732912.4704964) [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9293010
- No: 3 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9751699
+ No: 2 GFLOPS: 3.17/3.17 result: MeasureResult(costs=(0.07312442775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.387472152709961, timestamp=1675748741.5792985) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3007064
+ No: 3 GFLOPS: 0.00/3.17 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, 2, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7795425
+ No: 4 GFLOPS: 31.14/31.14 result: MeasureResult(costs=(0.007434278714285715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.857502222061157, timestamp=1675748744.4044824) [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4713313
+ No: 5 GFLOPS: 60.19/60.19 result: MeasureResult(costs=(0.003846041475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5972959995269775, timestamp=1675748747.2664506) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4744300
+ No: 6 GFLOPS: 0.00/60.19 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
@@ -514,8 +534,8 @@ 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, 128, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7573571
- No: 4 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4921830
+ No: 7 GFLOPS: 0.00/60.19 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
@@ -637,8 +657,8 @@ 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, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7753038
- No: 5 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10053592
+ No: 8 GFLOPS: 0.00/60.19 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
@@ -760,8 +780,8 @@ 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, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6568056
- No: 6 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3340794
+ No: 9 GFLOPS: 0.00/60.19 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
@@ -883,9 +903,8 @@ 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, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7928888
- No: 7 GFLOPS: 5.75/28.55 result: MeasureResult(costs=(0.0402826575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0895698070526123, timestamp=1675732916.6339478) [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5493417
- No: 8 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3301743
+ No: 10 GFLOPS: 0.00/60.19 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
@@ -1007,9 +1026,8 @@ 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, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1204548
- No: 9 GFLOPS: 34.21/34.21 result: MeasureResult(costs=(0.00676794640909091,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0776684284210205, timestamp=1675732924.4722035) [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,68293
- No: 10 GFLOPS: 0.00/34.21 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10083541
+ No: 11 GFLOPS: 0.00/60.19 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
@@ -1131,11 +1149,8 @@ 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, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8311525
- No: 11 GFLOPS: 40.97/40.97 result: MeasureResult(costs=(0.005650901333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4330289363861084, timestamp=1675732925.2379646) [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9394916
- No: 12 GFLOPS: 45.30/45.30 result: MeasureResult(costs=(0.005110728050000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.2402074337005615, timestamp=1675732925.9959552) [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8977051
- No: 13 GFLOPS: 18.14/45.30 result: MeasureResult(costs=(0.012761294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4122967720031738, timestamp=1675732937.180015) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('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', 1)],None,5699320
- No: 14 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8882606
+ No: 12 GFLOPS: 0.00/60.19 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
@@ -1257,8 +1272,8 @@ 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, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6647285
- No: 15 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6033002
+ No: 13 GFLOPS: 0.00/60.19 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
@@ -1380,26 +1395,8 @@ 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, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2861227
- No: 16 GFLOPS: 0.00/45.30 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, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9277896
- No: 17 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8311110
+ No: 14 GFLOPS: 0.00/60.19 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
@@ -1521,8 +1518,8 @@ 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, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7584800
- No: 18 GFLOPS: 0.00/45.30 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, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4319686
+ No: 15 GFLOPS: 0.00/60.19 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
@@ -1644,8 +1641,8 @@ 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, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8031143
- No: 19 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5982706
+ No: 16 GFLOPS: 0.00/60.19 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
@@ -1767,8 +1764,9 @@ 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, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6714008
- No: 20 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7126835
+ No: 17 GFLOPS: 63.28/63.28 result: MeasureResult(costs=(0.0036586410333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3199729919433594, timestamp=1675748750.9378455) [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,776724
+ No: 18 GFLOPS: 0.00/63.28 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
@@ -1890,7 +1888,9 @@ 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, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7492272
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8931815
+ No: 19 GFLOPS: 40.19/63.28 result: MeasureResult(costs=(0.005760213166666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9801359176635742, timestamp=1675748751.6873171) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7237241
+ No: 20 GFLOPS: 30.99/63.28 result: MeasureResult(costs=(0.007470207714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9747631549835205, timestamp=1675748752.4501755) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9940581
@@ -1945,9 +1945,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8977051
+ [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,776724
Finish loading 20 records
- Time cost of this operator: 0.005486
+ Time cost of this operator: 0.003737
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 a2e6974d35..6a481ccc59 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
@@ -360,10 +360,10 @@ 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 305.5 98.444 (1, 2, 10, 10, 3) 2 1 [305.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.782 1.219 (1, 6, 10, 10) 1 1 [3.782]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.047 0.337 (1, 1, 10, 10, 3) 1 1 [1.047]
- Total_time - 310.328 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 357.8 98.876 (1, 2, 10, 10, 3) 2 1 [357.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.111 0.86 (1, 6, 10, 10) 1 1 [3.111]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.264 (1, 1, 10, 10, 3) 1 1 [0.956]
+ Total_time - 361.866 - - - - -
@@ -428,10 +428,10 @@ 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 127.1 97.991 (1, 6, 10, 10, 1) 2 1 [127.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 1.362 (1, 6, 10, 10) 1 1 [1.767]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.839 0.647 (1, 3, 10, 10, 1) 1 1 [0.839]
- Total_time - 129.706 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.0 97.343 (1, 6, 10, 10, 1) 2 1 [100.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.704 (1, 6, 10, 10) 1 1 [1.75]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.979 0.953 (1, 1, 10, 10, 3) 1 1 [0.979]
+ Total_time - 102.73 - - - - -
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 03e41a14cb..9c6974b09f 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
@@ -118,7 +118,7 @@ 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]
61%|###### | 2.09M/3.42M [00:00<00:00, 19.7MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 30.7MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 70.4MB/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.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.966 seconds)
+ **Total running time of the script:** ( 1 minutes 8.852 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 948ec040fb..9784d269b2 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
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpdqejwjxp/images/random'
+ '/tmp/tmp1d07iyxf/images/random'
@@ -309,7 +309,7 @@ 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], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpdqejwjxp/images/target contains 8144 images
- /tmp/tmpdqejwjxp/images/random contains 5000 images
+ /tmp/tmp1d07iyxf/images/target contains 8144 images
+ /tmp/tmp1d07iyxf/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 46s - loss: 0.2308 - accuracy: 0.9217 - val_loss: 0.1090 - val_accuracy: 0.9592 - 46s/epoch - 139ms/step
+ 328/328 - 47s - loss: 0.2308 - accuracy: 0.9170 - val_loss: 0.1005 - val_accuracy: 0.9630 - 47s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1020 - accuracy: 0.9628 - val_loss: 0.1442 - val_accuracy: 0.9494 - 43s/epoch - 130ms/step
+ 328/328 - 43s - loss: 0.1003 - accuracy: 0.9613 - val_loss: 0.0943 - val_accuracy: 0.9675 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 42s - loss: 0.0685 - accuracy: 0.9747 - val_loss: 0.0729 - val_accuracy: 0.9785 - 42s/epoch - 129ms/step
+ 328/328 - 43s - loss: 0.0679 - accuracy: 0.9748 - val_loss: 0.1147 - val_accuracy: 0.9626 - 43s/epoch - 130ms/step
- <keras.callbacks.History object at 0x7f672c502090>
+ <keras.callbacks.History object at 0x7fb538580e90>
@@ -861,7 +861,7 @@ 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 51.511 seconds)
+ **Total running time of the script:** ( 4 minutes 35.377 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 bb98d781bb..96fa3732b2 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
=================
-**07:04.781** total execution time for **how_to_work_with_microtvm** files:
+**06:49.992** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:51.511 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:35.377 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:08.966 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:08.852 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.607 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:52.699 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.729 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.736 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.968 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:05.328 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 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 466c82afd2..d4597d1710 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
=================
-**00:43.616** total execution time for **how_to_work_with_relay** files:
+**00:44.474** 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``) | 00:31.831 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.986 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.150 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.728 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.629 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.754 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 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 3503313c6e..ff09ff1baa 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
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f65d7cd0830>
+ <function my_cuda_math_rule at 0x7fb3e39514d0>
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 041ab4dbbf..12f2230dd8 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
@@ -5,18 +5,18 @@
Computation times
=================
-**00:08.514** total execution time for **how_to_work_with_schedules** files:
+**00:06.958** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.088 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.216 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.076 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.393 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.570 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.572 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.553 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.551 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 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 cdae719741..a495da2f50 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -340,7 +340,7 @@ The importing needs to happen before the tensorized GEMV being executed.
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpaufvpqlw/input0.cc'\nsource_filename = \"/tmp/tmpaufvpqlw/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 float*, [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpo4rpwrns/input0.cc'\nsource_filename = \"/tmp/tmpo4rpwrns/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 float*, [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
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 989b72ebf1..6340d70ede 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
=================
-**00:29.602** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:29.525** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:29.596 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:29.519 | 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 429bef0425..51bbc964e9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ 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 31.64s!
+ resnet18_v1 inference graph built in 31.32s!
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 55caa3d0ec..dcb994f988 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ 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 21.60s!
+ yolov3-tiny inference graph built in 21.49s!
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 791def4c79..acfaae5b0f 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
=================
-**01:36.504** total execution time for **topic_vta_tutorials_frontend** files:
+**01:36.723** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.316 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.541 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.188 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.182 | 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 1b1033022e..8e1b6b7d9a 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
=================
-**00:03.099** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.159** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.648 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.704 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.451 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.455 | 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 a9b1c3aa86..d1a8607f6f 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
=================
-**00:00.757** total execution time for **topic_vta_tutorials** files:
+**00:00.764** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.391 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.395 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.366 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.369 | 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 a6b800d616..ee642f7e57 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,13 +207,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -325,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 97.662 ms
+ Execution time of this operator: 96.660 ms
@@ -443,7 +436,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 44.694 seconds)
+ **Total running time of the script:** ( 1 minutes 19.703 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 1ca1a1fc0a..75e5fa29b2 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.90/0.90 result: MeasureResult(costs=(0.299862836,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.03689432144165, timestamp=1675731344.0013065) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
- No: 2 GFLOPS: 12.15/12.15 result: MeasureResult(costs=(0.0220975426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6425826549530029, timestamp=1675731344.6250105) [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
- No: 3 GFLOPS: 2.45/12.15 result: MeasureResult(costs=(0.10952323280000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9926838874816895, timestamp=1675731347.417639) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
- No: 4 GFLOPS: 11.58/12.15 result: MeasureResult(costs=(0.0231780338,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6277921199798584, timestamp=1675731348.833036) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
- No: 5 GFLOPS: 9.66/12.15 result: MeasureResult(costs=(0.0277882664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7126765251159668, timestamp=1675731349.6715972) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 6 GFLOPS: 3.26/12.15 result: MeasureResult(costs=(0.0822948214,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5707828998565674, timestamp=1675731352.0310268) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
- No: 7 GFLOPS: 13.11/13.11 result: MeasureResult(costs=(0.0204715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5757625102996826, timestamp=1675731352.6155608) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
- No: 8 GFLOPS: 1.63/13.11 result: MeasureResult(costs=(0.1642668912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8583526611328125, timestamp=1675731355.4997556) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
- No: 9 GFLOPS: 12.81/13.11 result: MeasureResult(costs=(0.0209598278,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6403548717498779, timestamp=1675731356.255377) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
- No: 10 GFLOPS: 2.12/13.11 result: MeasureResult(costs=(0.1263718674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2205970287323, timestamp=1675731358.5252938) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+ No: 1 GFLOPS: 1.10/1.10 result: MeasureResult(costs=(0.2436254098,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.11844801902771, timestamp=1675747216.887491) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+ No: 2 GFLOPS: 0.87/1.10 result: MeasureResult(costs=(0.3079831106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.148522853851318, timestamp=1675747222.0631766) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 3 GFLOPS: 8.70/8.70 result: MeasureResult(costs=(0.030843296400000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8636910915374756, timestamp=1675747223.547771) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+ No: 4 GFLOPS: 2.72/8.70 result: MeasureResult(costs=(0.0985271742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8010296821594238, timestamp=1675747226.121015) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
+ No: 5 GFLOPS: 3.66/8.70 result: MeasureResult(costs=(0.0732860996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4052789211273193, timestamp=1675747227.6757784) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+ No: 6 GFLOPS: 2.44/8.70 result: MeasureResult(costs=(0.11006655800000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9935088157653809, timestamp=1675747229.6874518) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 7 GFLOPS: 3.93/8.70 result: MeasureResult(costs=(0.06836141300000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3519701957702637, timestamp=1675747231.779376) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+ No: 8 GFLOPS: 2.60/8.70 result: MeasureResult(costs=(0.10330509380000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8996071815490723, timestamp=1675747233.6836398) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
+ No: 9 GFLOPS: 1.51/8.70 result: MeasureResult(costs=(0.17792393899999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.047940969467163, timestamp=1675747236.8452926) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+ No: 10 GFLOPS: 2.84/8.70 result: MeasureResult(costs=(0.0944473306,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7110950946807861, timestamp=1675747238.6050239) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 6a35509a72..218463e804 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 518.7866215400004, 'median': 518.8077074000034, 'std': 2.279827303963719}
+ {'mean': 509.7426279499985, 'median': 509.1296362000037, 'std': 2.4044555332396995}
@@ -545,28 +545,30 @@ 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: 8.81/ 15.21 GFLOPS | Progress: (4/20) | 9.16 s
[Task 1/25] Current/Best: 13.45/ 23.51 GFLOPS | Progress: (8/20) | 13.27 s
[Task 1/25] Current/Best: 8.95/ 23.51 GFLOPS | Progress: (12/20) | 16.55 s
[Task 1/25] Current/Best: 10.78/ 23.51 GFLOPS | Progress: (16/20) | 18.87 s
[Task 1/25] Current/Best: 14.21/ 23.51 GFLOPS | Progress: (20/20) | 22.93 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 14.90/ 21.68 GFLOPS | Progress: (4/20) | 3.72 s
[Task 2/25] Current/Best: 16.14/ 21.68 GFLOPS | Progress: (8/20) | 5.77 s
[Task 2/25] Current/Best: 11.91/ 21.68 GFLOPS | Progress: (12/20) | 7.42 s
[Task 2/25] Current/Best: 11.38/ 21.68 GFLOPS | Progress: (16/20) | 9.01 s
[Task 2/25] Current/Best: 21.63/ 21.68 GFLOPS | Progress: (20/20) | 10.76 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.87/ 15.87 GFLOPS | Progress: (4/20) | 6.03 s
[Task 3/25] Current/Best: 23.02/ 23.02 GFLOPS | Progress: (8/20) | 9.50 s
[Task 3/25] Current/Best: 10.94/ 23.02 GFLOPS | Progress: (12/20) | 12.95 s
[Task 3/25] Current/Best: 19.11/ 23.02 GFLOPS | Progress: (16/20) | 15.98 s
[Task 3/25] Current/Best: 11.79/ 23.02 GFLOPS | Progress: (20/20) | 18.20 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.02/ 15.29 GFLOPS | Progress: (4/20) | 4.78 s
[Task 4/25] Current/Best: 10.25/ 15.29 GFLOPS | Progress: (8/20) | 8.04 s
[Task 4/25] Current/Best: 10.83/ 17.75 GFLOPS | Progress: (12/20) | 12.39 s
[Task 4/25] Current/Best: 17.59/ 21.83 GFLOPS | Progress: (16/20) | 14.73 s
[Task 4/25] Current/Best: 16.46/ 21.83 GFLOPS | Progress: (20/20) | 16.81 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 5.40/ 18.27 GFLOPS | Progress: (4/20) | 3.81 s
[Task 5/25] Current/Best: 19.87/ 19.87 GFLOPS | Progress: (8/20) | 5.71 s
[Task 5/25] Current/Best: 13.98/ 19.87 GFLOPS | Progress: (12/20) | 9.39 s
[Task 5/25] Current/Best: 11.18/ 19.87 GFLOPS | Progress: (16/20) | 11.96 s
[Task 5/25] Current/Best: 5.36/ 19.87 GFLOPS | Progress: (20/20) | 13.83 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (4/20) | 4.51 s
[Task 6/25] Current/Best: 10.03/ 17.47 GFLOPS | Progress: (8/20) | 8.82 s
[Task 6/25] Current/Best: 14.53/ 19.73 GFLOPS | Progress: (12/20) | 11.18 s
[Task 6/25] Current/Best: 13.01/ 19.73 GFLOPS | Progress: (16/20) | 14.32 s
[Task 6/25] Current/Best: 16.34/ 19.73 GFLOPS | Progress: (20/20) | 19.73 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.35/ 15.35 GFLOPS | Progress: (4/20) | 4.15 s
[Task 7/25] Current/Best: 10.77/ 15.55 GFLOPS | Progress: (8/20) | 7.50 s
[Task 7/25] Current/Best: 10.62/ 22.88 GFLOPS | Progress: (12/20) | 10.97 s
[Task 7/25] Current/Best: 16.00/ 22.88 GFLOPS | Progress: (16/20) | 13.60 s
[Task 7/25] Current/Best: 17.68/ 22.88 GFLOPS | Progress: (20/20) | 16.32 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 13.42/ 13.42 GFLOPS | Progress: (4/20) | 4.22 s
[Task 8/25] Current/Best: 12.19/ 13.51 GFLOPS | Progress: (8/20) | 7.28 s
[Task 8/25] Current/Best: 2.44/ 13.51 GFLOPS | Progress: (12/20) | 11.73 s
[Task 8/25] Current/Best: 7.67/ 13.51 GFLOPS | Progress: (16/20) | 18.12 s
[Task 8/25] Current/Best: 5.56/ 15.01 GFLOPS | Progress: (20/20) | 20.45 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 9.03/ 10.36 GFLOPS | Progress: (4/20) | 11.99 s
[Task 9/25] Current/Best: 16.37/ 16.37 GFLOPS | Progress: (8/20) | 17.39 s
[Task 9/25] Current/Best: 19.88/ 19.88 GFLOPS | Progress: (12/20) | 19.01 s
[Task 9/25] Current/Best: 6.81/ 19.88 GFLOPS | Progress: (16/20) | 30.45 s
[Task 9/25] Current/Best: 12.94/ 19.88 GFLOPS | Progress: (20/20) | 33.36 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.69/ 20.15 GFLOPS | Progress: (4/20) | 4.95 s
[Task 10/25] Current/Best: 8.98/ 20.43 GFLOPS | Progress: (8/20) | 6.89 s
[Task 10/25] Current/Best: 9.80/ 20.43 GFLOPS | Progress: (12/20) | 10.29 s
[Task 10/25] Current/Best: 11.48/ 20.43 GFLOPS | Progress: (16/20) | 12.10 s
[Task 10/25] Current/Best: 14.22/ 20.43 GFLOPS | Progress: (20/20) | 13.85 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 17.78/ 21.19 GFLOPS | Progress: (4/20) | 4.04 s
[Task 11/25] Current/Best: 9.57/ 22.08 GFLOPS | Progress: (8/20) | 6.50 s
[Task 11/25] Current/Best: 7.14/ 22.08 GFLOPS | Progress: (12/20) | 9.94 s
[Task 11/25] Current/Best: 20.95/ 22.08 GFLOPS | Progress: (16/20) | 12.39 s
[Task 11/25] Current/Best: 12.08/ 22.08 GFLOPS | Progress: (20/20) | 15.17 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (4/20) | 4.34 s
[Task 12/25] Current/Best: 5.10/ 18.46 GFLOPS | Progress: (8/20) | 7.49 s
[Task 12/25] Current/Best: 5.69/ 21.28 GFLOPS | Progress: (12/20) | 10.86 s
[Task 12/25] Current/Best: 12.44/ 21.28 GFLOPS | Progress: (16/20) | 14.29 s
[Task 12/25] Current/Best: 7.93/ 21.28 GFLOPS | Progress: (20/20) | 16.46 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 13.34/ 13.34 GFLOPS | Progress: (4/20) | 4.49 s
[Task 13/25] Current/Best: 10.71/ 14.00 GFLOPS | Progress: (8/20) | 8.21 s
[Task 13/25] Current/Best: 9.84/ 23.32 GFLOPS | Progress: (12/20) | 11.39 s
[Task 13/25] Current/Best: 8.38/ 23.32 GFLOPS | Progress: (16/20) | 14.80 s
[Task 13/25] Current/Best: 11.07/ 23.32 GFLOPS | Progress: (20/20) | 18.40 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 4.31/ 10.20 GFLOPS | Progress: (4/20) | 6.42 s
[Task 14/25] Current/Best: 9.50/ 15.77 GFLOPS | Progress: (8/20) | 9.74 s
[Task 14/25] Current/Best: 9.41/ 15.77 GFLOPS | Progress: (12/20) | 16.71 s
[Task 14/25] Current/Best: 3.02/ 15.77 GFLOPS | Progress: (16/20) | 20.13 s
[Task 14/25] Current/Best: 14.33/ 15.77 GFLOPS | Progress: (20/20) | 22.09 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 11.40/ 13.23 GFLOPS | Progress: (4/20) | 7.17 s Done.
-
[Task 15/25] Current/Best: 17.11/ 17.11 GFLOPS | Progress: (8/20) | 10.48 s
[Task 15/25] Current/Best: 14.90/ 17.11 GFLOPS | Progress: (12/20) | 13.16 s
[Task 15/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (16/20) | 17.87 s
[Task 15/25] Current/Best: 9.18/ 17.41 GFLOPS | Progress: (20/20) | 21.50 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.04/ 18.35 GFLOPS | Progress: (4/20) | 4.11 s
[Task 16/25] Current/Best: 9.65/ 18.35 GFLOPS | Progress: (8/20) | 6.46 s
[Task 16/25] Current/Best: 15.72/ 21.86 GFLOPS | Progress: (12/20) | 8.20 s
[Task 16/25] Current/Best: 18.75/ 21.86 GFLOPS | Progress: (16/20) | 9.70 s
[Task 16/25] Current/Best: 10.68/ 21.86 GFLOPS | Progress: (20/20) | 11.25 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 21.50/ 21.50 GFLOPS | Progress: (4/20) | 4.14 s
[Task 17/25] Current/Best: 7.63/ 21.50 GFLOPS | Progress: (8/20) | 6.63 s
[Task 17/25] Current/Best: 9.99/ 22.42 GFLOPS | Progress: (12/20) | 10.34 s
[Task 17/25] Current/Best: 6.20/ 22.42 GFLOPS | Progress: (16/20) | 14.93 s
[Task 17/25] Current/Best: 11.99/ 23.15 GFLOPS | Progress: (20/20) | 17.27 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 6.95/ 18.79 GFLOPS | Progress: (4/20) | 5.56 s
[Task 18/25] Current/Best: 10.15/ 22.70 GFLOPS | Progress: (8/20) | 8.71 s
[Task 18/25] Current/Best: 9.63/ 22.70 GFLOPS | Progress: (12/20) | 11.25 s
[Task 18/25] Current/Best: 17.61/ 22.70 GFLOPS | Progress: (16/20) | 13.04 s
[Task 18/25] Current/Best: 16.98/ 22.70 GFLOPS | Progress: (20/20) | 16.68 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.80/ 21.80 GFLOPS | Progress: (4/20) | 4.40 s
[Task 19/25] Current/Best: 18.20/ 21.80 GFLOPS | Progress: (8/20) | 8.01 s
[Task 19/25] Current/Best: 14.65/ 21.80 GFLOPS | Progress: (12/20) | 10.27 s
[Task 19/25] Current/Best: 10.16/ 21.80 GFLOPS | Progress: (16/20) | 14.06 s
[Task 19/25] Current/Best: 9.14/ 21.80 GFLOPS | Progress: (20/20) | 18.05 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 1.58/ 9.20 GFLOPS | Progress: (4/20) | 6.05 s
[Task 20/25] Current/Best: 17.41/ 18.93 GFLOPS | Progress: (8/20) | 8.79 s
[Task 20/25] Current/Best: 10.39/ 18.93 GFLOPS | Progress: (12/20) | 11.82 s
[Task 20/25] Current/Best: 8.33/ 18.93 GFLOPS | Progress: (16/20) | 14.71 s
[Task 20/25] Current/Best: 5.15/ 18.93 GFLOPS | Progress: (20/20) | 17.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 16.24/ 16.24 GFLOPS | Progress: (4/20) | 4.86 s
[Task 21/25] Current/Best: 16.53/ 20.19 GFLOPS | Progress: (8/20) | 6.88 s
[Task 21/25] Current/Best: 2.74/ 20.19 GFLOPS | Progress: (12/20) | 9.66 s
[Task 21/25] Current/Best: 10.36/ 20.19 GFLOPS | Progress: (16/20) | 12.24 s
[Task 21/25] Current/Best: 7.02/ 20.19 GFLOPS | Progress: (20/20)
| 14.50 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 16.21/ 18.26 GFLOPS | Progress: (4/20) | 4.50 s
[Task 22/25] Current/Best: 5.33/ 18.71 GFLOPS | Progress: (8/20) | 7.95 s
[Task 22/25] Current/Best: 16.92/ 18.71 GFLOPS | Progress: (12/20) | 10.26 s
[Task 22/25] Current/Best: 9.43/ 18.71 GFLOPS | Progress: (16/20) | 14.12 s
[Task 22/25] Current/Best: 10.56/ 19.23 GFLOPS | Progress: (20/20) | 16.77 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 15.57/ 23.76 GFLOPS | Progress: (4/20) | 4.23 s
[Task 23/25] Current/Best: 12.11/ 23.76 GFLOPS | Progress: (8/20) | 7.49 s
[Task 23/25] Current/Best: 2.69/ 23.76 GFLOPS | Progress: (12/20) | 10.63 s
[Task 23/25] Current/Best: 18.81/ 23.76 GFLOPS | Progress: (16/20) | 13.69 s
[Task 23/25] Current/Best: 20.58/ 23.76 GFLOPS | Progress: (20/20) | 16.25 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.07/ 8.07 GFLOPS | Progress: (4/20) | 12.76 s
[Task 24/25] Current/Best: 3.54/ 8.84 GFLOPS | Progress: (8/20) | 16.31 s
[Task 24/25] Current/Best: 1.91/ 8.84 GFLOPS | Progress: (12/20) | 27.27 s Done.
-
[Task 24/25] Current/Best: 2.20/ 8.84 GFLOPS | Progress: (16/20) | 32.10 s
[Task 24/25] Current/Best: 3.43/ 8.84 GFLOPS | Progress: (20/20) | 43.07 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.37/ 7.72 GFLOPS | Progress: (4/20) | 3.98 s
[Task 25/25] Current/Best: 8.61/ 8.61 GFLOPS | Progress: (8/20) | 5.66 s
[Task 25/25] Current/Best: 1.56/ 8.61 GFLOPS | Progress: (12/20) | 16.36 s
[Task 25/25] Current/Best: 8.93/ 8.93 GFLOPS | Progress: (16/20) | 28.04 s
[Task 25/25] Current/Best: 5.64/ 8.93 GFLOPS | Progress: (20/20) | 40.08 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 9.56/ 22.61 GFLOPS | Progress: (4/20) | 8.95 s
[Task 1/25] Current/Best: 9.69/ 22.61 GFLOPS | Progress: (8/20) | 15.86 s
[Task 1/25] Current/Best: 11.24/ 22.61 GFLOPS | Progress: (12/20) | 18.47 s
[Task 1/25] Current/Best: 8.57/ 23.55 GFLOPS | Progress: (16/20) | 20.53 s
[Task 1/25] Current/Best: 12.32/ 23.55 GFLOPS | Progress: (20/20) | 23.60 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.67/ 19.97 GFLOPS | Progress: (4/20) | 3.58 s
[Task 2/25] Current/Best: 13.51/ 19.97 GFLOPS | Progress: (8/20) | 5.26 s
[Task 2/25] Current/Best: 8.06/ 19.97 GFLOPS | Progress: (12/20) | 7.21 s
[Task 2/25] Current/Best: 7.46/ 19.97 GFLOPS | Progress: (16/20) | 9.53 s
[Task 2/25] Current/Best: 20.05/ 20.05 GFLOPS | Progress: (20/20) | 10.83 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.63/ 19.40 GFLOPS | Progress: (4/20) | 3.82 s
[Task 3/25] Current/Best: 7.35/ 19.40 GFLOPS | Progress: (8/20) | 6.37 s
[Task 3/25] Current/Best: 16.73/ 22.80 GFLOPS | Progress: (12/20) | 8.50 s
[Task 3/25] Current/Best: 6.11/ 22.80 GFLOPS | Progress: (16/20) | 11.26 s
[Task 3/25] Current/Best: 6.48/ 22.80 GFLOPS | Progress: (20/20) | 14.62 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 6.11/ 13.83 GFLOPS | Progress: (4/20) | 6.29 s
[Task 4/25] Current/Best: 5.68/ 21.70 GFLOPS | Progress: (8/20) | 8.05 s
[Task 4/25] Current/Best: 11.73/ 21.70 GFLOPS | Progress: (12/20) | 10.92 s
[Task 4/25] Current/Best: 20.33/ 21.70 GFLOPS | Progress: (16/20) | 17.42 s
[Task 4/25] Current/Best: 6.51/ 21.70 GFLOPS | Progress: (20/20) | 22.17 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.64/ 15.38 GFLOPS | Progress: (4/20) | 3.87 s
[Task 5/25] Current/Best: 10.95/ 15.38 GFLOPS | Progress: (8/20) | 6.49 s
[Task 5/25] Current/Best: 3.49/ 15.38 GFLOPS | Progress: (12/20) | 9.03 s
[Task 5/25] Current/Best: 10.85/ 15.38 GFLOPS | Progress: (16/20) | 11.10 s
[Task 5/25] Current/Best: 12.97/ 20.27 GFLOPS | Progress: (20/20) | 13.12 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 13.84/ 16.06 GFLOPS | Progress: (4/20) | 4.54 s
[Task 6/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (8/20) | 7.63 s
[Task 6/25] Current/Best: 8.53/ 18.11 GFLOPS | Progress: (12/20) | 10.58 s
[Task 6/25] Current/Best: 11.07/ 20.14 GFLOPS | Progress: (16/20) | 14.28 s
[Task 6/25] Current/Best: 4.38/ 20.14 GFLOPS | Progress: (20/20) | 18.20 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 14.47/ 19.43 GFLOPS | Progress: (4/20) | 3.91 s
[Task 7/25] Current/Best: 15.61/ 19.43 GFLOPS | Progress: (8/20) | 7.02 s
[Task 7/25] Current/Best: 9.68/ 22.59 GFLOPS | Progress: (12/20) | 9.87 s
[Task 7/25] Current/Best: 17.25/ 22.59 GFLOPS | Progress: (16/20) | 11.71 s
[Task 7/25] Current/Best: 17.74/ 22.59 GFLOPS | Progress: (20/20) | 13.71 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.72/ 21.48 GFLOPS | Progress: (4/20) | 4.83 s
[Task 8/25] Current/Best: 7.97/ 21.48 GFLOPS | Progress: (8/20) | 7.04 s
[Task 8/25] Current/Best: 19.86/ 21.48 GFLOPS | Progress: (12/20) | 10.35 s
[Task 8/25] Current/Best: 10.01/ 21.48 GFLOPS | Progress: (16/20) | 15.14 s
[Task 8/25] Current/Best: 12.62/ 21.48 GFLOPS | Progress: (20/20) | 23.83 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 6.05/ 16.87 GFLOPS | Progress: (4/20) | 6.67 s
[Task 9/25] Current/Best: 12.87/ 18.93 GFLOPS | Progress: (8/20) | 9.15 s
[Task 9/25] Current/Best: 4.79/ 18.93 GFLOPS | Progress: (12/20) | 19.91 s
[Task 9/25] Current/Best: 6.48/ 18.93 GFLOPS | Progress: (16/20) | 21.71 s
[Task 9/25] Current/Best: 11.39/ 18.93 GFLOPS | Progress: (20/20) | 25.43 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 10.81/ 15.29 GFLOPS | Progress: (4/20) | 5.58 s
[Task 10/25] Current/Best: 14.17/ 17.03 GFLOPS | Progress: (8/20) | 7.47 s
[Task 10/25] Current/Best: 11.83/ 17.03 GFLOPS | Progress: (12/20) | 10.11 s
[Task 10/25] Current/Best: 17.74/ 17.74 GFLOPS | Progress: (16/20) | 13.27 s
[Task 10/25] Current/Best: 10.40/ 17.74 GFLOPS | Progress: (20/20) | 15.17 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.98/ 16.44 GFLOPS | Progress: (4/20) | 4.62 s
[Task 11/25] Current/Best: 12.63/ 22.20 GFLOPS | Progress: (8/20) | 7.02 s
[Task 11/25] Current/Best: 3.13/ 22.20 GFLOPS | Progress: (12/20) | 11.50 s
[Task 11/25] Current/Best: 8.59/ 22.20 GFLOPS | Progress: (16/20) | 13.71 s
[Task 11/25] Current/Best: 11.38/ 22.20 GFLOPS | Progress: (20/20) | 17.18 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 5.20/ 16.03 GFLOPS | Progress: (4/20) | 7.53 s
[Task 12/25] Current/Best: 3.62/ 18.56 GFLOPS | Progress: (8/20) | 10.19 s
[Task 12/25] Current/Best: 17.33/ 18.56 GFLOPS | Progress: (12/20) | 16.21 s
[Task 12/25] Current/Best: 4.55/ 18.56 GFLOPS | Progress: (16/20) | 18.98 s
[Task 12/25] Current/Best: 14.94/ 21.68 GFLOPS | Progress: (20/20) | 22.16 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.79/ 15.93 GFLOPS | Progress: (4/20) | 4.19 s
[Task 13/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (8/20) | 6.75 s
[Task 13/25] Current/Best: 8.15/ 20.26 GFLOPS | Progress: (12/20) | 9.15 s
[Task 13/25] Current/Best: 18.40/ 20.26 GFLOPS | Progress: (16/20) | 12.00 s
[Task 13/25] Current/Best: 7.01/ 20.26 GFLOPS | Progress: (20/20) | 15.03 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.88/ 18.96 GFLOPS | Progress: (4/20) | 7.15 s
[Task 14/25] Current/Best: 9.46/ 18.96 GFLOPS | Progress: (8/20) | 11.03 s
[Task 14/25] Current/Best: 11.71/ 18.96 GFLOPS | Progress: (12/20) | 15.02 s
[Task 14/25] Current/Best: 9.15/ 18.96 GFLOPS | Progress: (16/20) | 20.12 s
[Task 14/25] Current/Best: 11.89/ 18.96 GFLOPS | Progress: (20/20) | 23.06 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 10.22/ 13.80 GFLOPS | Progress: (4/20) | 5.07 s
[Task 15/25] Current/Best: 9.50/ 20.43 GFLOPS | Progress: (8/20) | 10.42 s
[Task 15/25] Current/Best: 13.33/ 20.43 GFLOPS | Progress: (12/20) | 13.15 s
[Task 15/25] Current/Best: 15.53/ 20.43 GFLOPS | Progress: (16/20) | 16.47 s
[Task 15/25] Current/Best: 10.94/ 20.43 GFLOPS | Progress: (20/
20) | 20.50 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 15.97/ 15.97 GFLOPS | Progress: (4/20) | 3.36 s
[Task 16/25] Current/Best: 5.19/ 16.15 GFLOPS | Progress: (8/20) | 5.25 s
[Task 16/25] Current/Best: 11.57/ 21.21 GFLOPS | Progress: (12/20) | 8.05 s
[Task 16/25] Current/Best: 10.61/ 21.21 GFLOPS | Progress: (16/20) | 11.46 s
[Task 16/25] Current/Best: 9.89/ 21.21 GFLOPS | Progress: (20/20) | 14.61 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.81/ 17.55 GFLOPS | Progress: (4/20) | 4.14 s
[Task 17/25] Current/Best: 19.63/ 19.63 GFLOPS | Progress: (8/20) | 6.48 s
[Task 17/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (12/20) | 8.91 s
[Task 17/25] Current/Best: 18.96/ 21.76 GFLOPS | Progress: (16/20) | 10.88 s
[Task 17/25] Current/Best: 19.90/ 21.76 GFLOPS | Progress: (20/20) | 13.32 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.71/ 10.71 GFLOPS | Progress: (4/20) | 5.93 s
[Task 18/25] Current/Best: 5.22/ 15.61 GFLOPS | Progress: (8/20) | 10.81 s
[Task 18/25] Current/Best: 14.84/ 16.46 GFLOPS | Progress: (12/20) | 13.28 s
[Task 18/25] Current/Best: 12.42/ 16.46 GFLOPS | Progress: (16/20) | 15.56 s
[Task 18/25] Current/Best: 2.98/ 21.51 GFLOPS | Progress: (20/20) | 18.72 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.19/ 12.17 GFLOPS | Progress: (4/20) | 5.54 s
[Task 19/25] Current/Best: 5.03/ 20.38 GFLOPS | Progress: (8/20) | 8.42 s
[Task 19/25] Current/Best: 5.37/ 21.17 GFLOPS | Progress: (12/20) | 12.64 s
[Task 19/25] Current/Best: 10.04/ 21.17 GFLOPS | Progress: (16/20) | 16.07 s
[Task 19/25] Current/Best: 3.10/ 21.17 GFLOPS | Progress: (20/20) | 20.06 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 4.18/ 18.72 GFLOPS | Progress: (4/20) | 9.75 s
[Task 20/25] Current/Best: 3.11/ 18.72 GFLOPS | Progress: (8/20) | 13.95 s
[Task 20/25] Current/Best: 18.04/ 18.72 GFLOPS | Progress: (12/20) | 18.13 s Done.
+
[Task 20/25] Current/Best: 5.32/ 20.63 GFLOPS | Progress: (16/20) | 20.63 s
[Task 20/25] Current/Best: 7.41/ 20.63 GFLOPS | Progress: (20/20) | 24.47 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 18.54/ 18.54 GFLOPS | Progress: (4/20) | 4.47 s
[Task 21/25] Current/Best: 11.06/ 18.54 GFLOPS | Progress: (8/20) | 7.38 s
[Task 21/25] Current/Best: 15.77/ 18.54 GFLOPS | Progress: (12/20) | 9.14 s
[Task 21/25] Current/Best: 11.66/ 18.54 GFLOPS | Progress: (16/20) | 10.96 s
[Task 21/25] Current/Best: 12.27/ 18.54 GFLOPS | Progress: (20/20) | 13.14 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 5.29/ 13.31 GFLOPS | Progress: (4/20) | 5.18 s
[Task 22/25] Current/Best: 5.23/ 16.60 GFLOPS | Progress: (8/20) | 6.89 s
[Task 22/25] Current/Best: 10.34/ 18.15 GFLOPS | Progress: (12/20)
| 8.99 s
[Task 22/25] Current/Best: 4.54/ 18.80 GFLOPS | Progress: (16/20) | 10.69 s
[Task 22/25] Current/Best: 4.89/ 18.80 GFLOPS | Progress: (20/20) | 13.56 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 23.59/ 23.59 GFLOPS | Progress: (4/20) | 4.75 s
[Task 23/25] Current/Best: 12.46/ 23.59 GFLOPS | Progress: (8/20) | 8.06 s
[Task 23/25] Current/Best: 8.10/ 23.59 GFLOPS | Progress: (12/20) | 11.77 s
[Task 23/25] Current/Best: 3.09/ 23.59 GFLOPS | Progress: (16/20) | 17.41 s
[Task 23/25] Current/Best: 11.46/ 23.59 GFLOPS | Progress: (20/20) | 21.76 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.97/ 4.97 GFLOPS | Progress: (4/20) | 12.40 s
[Task 24/25] Current/Best: 3.64/ 5.87 GFLOPS | Progress: (8/20) | 20.72 s
[Task 24/25] Current/Best: 11.04/ 11.04 GFLOPS | Progress: (12/20) | 31.08 s
[Task 24/25] Current/Best: 5.17/ 11.04 GFLOPS | Progress: (16/20) | 43.26 s Done.
+
[Task 24/25] Current/Best: 3.59/ 11.04 GFLOPS | Progress: (20/20) | 54.11 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 8.85/ 9.83 GFLOPS | Progress: (4/20) | 3.09 s
[Task 25/25] Current/Best: 6.09/ 9.83 GFLOPS | Progress: (8/20) | 14.03 s
[Task 25/25] Current/Best: 3.46/ 9.83 GFLOPS | Progress: (12/20) | 25.73 s
[Task 25/25] Current/Best: 3.26/ 9.83 GFLOPS | Progress: (16/20) | 31.36 s
[Task 25/25] Current/Best: 6.64/ 9.83 GFLOPS | Progress: (20/20) | 32.98 s
@@ -663,7 +665,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -720,8 +722,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 409.0993514900015, 'median': 408.93897490001336, 'std': 1.269619223700886}
- unoptimized: {'mean': 518.7866215400004, 'median': 518.8077074000034, 'std': 2.279827303963719}
+ optimized: {'mean': 404.93442639999785, 'median': 404.55560110000306, 'std': 1.954751803786656}
+ unoptimized: {'mean': 509.7426279499985, 'median': 509.1296362000037, 'std': 2.4044555332396995}
@@ -744,7 +746,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 58.132 seconds)
+ **Total running time of the script:** ( 12 minutes 4.185 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 896c500eca..f85df1fc73 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.373e-07 secs/op
+ 1.374e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d70b0c82de..8065ba4e23 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -277,7 +277,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x1b7732e0)), stage(b, placeholder(b, 0x18ec0c80)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T [...]
+ [stage(a, placeholder(a, 0x9d5d270)), stage(b, placeholder(b, 0x287922c0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index efb6031231..5aaa7fc763 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**15:47.917** total execution time for **tutorial** files:
+**15:30.236** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:58.132 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:04.185 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:44.694 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:19.703 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.547 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:57.768 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.301 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.502 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.899 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:30.270 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.316 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.809 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.860 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.842 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.157 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 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 dbab3f83c1..58fcc2546e 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -286,7 +286,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000007
- naive: 0.000008
+ naive: 0.000007
@@ -392,7 +392,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000007
@@ -504,10 +504,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.589659999463038e-06 1.0
- naive 7.812900000000001e-06 1.1856302147055597
- parallel 6.304800000000001e-06 0.9567716696329933
- vector 2.45805e-05 3.7301621027493
+ numpy 7.3559300017223e-06 1.0
+ naive 6.6999e-06 0.9108161712293756
+ parallel 7.1356e-06 0.9700472949483325
+ vector 2.4636999999999998e-05 3.3492705877069997
@@ -928,7 +928,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019755
+ Numpy running time: 0.017494
@@ -986,7 +986,7 @@ optimizations.
.. code-block:: none
- none: 3.478896
+ none: 3.189715
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.320792
+ blocking: 0.292836
@@ -1170,7 +1170,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.344441
+ vectorization: 0.325126
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1236,7 +1236,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.127262
+ loop permutation: 0.115189
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1327,7 +1327,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109480
+ array packing: 0.109497
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1410,7 +1410,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111123
+ block caching: 0.110943
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1484,7 +1484,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146085
+ parallelization: 0.146016
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1554,13 +1554,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4788961036000003 1.0
- blocking 0.320792416 0.09221097912870709
- vectorization 0.3444411703 0.09900875451370003
- loop permutation 0.1272621283 0.036581181073015584
- array packing 0.10947950849999999 0.031469611405385
- block caching 0.1111227279 0.03194195071965759
- parallelization 0.146084965 0.04199175849167489
+ none 3.1897148015 1.0
+ blocking 0.2928355883 0.09180619789653002
+ vectorization 0.3251257146 0.10192939959619772
+ loop permutation 0.11518875720000002 0.03611255687995402
+ array packing 0.1094965139 0.0343279950447319
+ block caching 0.11094310430000001 0.034781512205363234
+ parallelization 0.14601616739999998 0.04577718588863625
@@ -1600,11 +1600,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 2.547 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 7153488156..8d4f7b7f6e 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-60fcb0dedeb1d05eb6a93cccbf76c2d4a42d7231
+5456fae77655fadf47f61a94e28027c6d39b1e7e
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index a1eb542bef..564fe8f557 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 19.704 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.673 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 0da144890d..737dfc7f5b 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<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 953ms/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 fc807ffc32..334c79465d 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
<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.zip13b06bfd-9422-40ff-8613-9bf21549111d 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.zip0718a6a2-1e6f-48f2-b9e9-fbe575dd14d7 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 2d71594e95..35acd28f20 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,12 +449,13 @@ 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]
- 19%|#9 | 7.99M/41.5M [00:00<00:01, 34.1MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 34.4MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 38.9MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 46.1MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 36.7MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 38.5MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 49.5MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 51.0MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 47.3MB/s]
+ 65%|######4 | 26.8M/41.5M [00:00<00:00, 37.6MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.4MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 41.8MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 42.6MB/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 d8fbff1900..c9a1928d47 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,14 +432,11 @@ 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]
- 14%|#4 | 6.30M/44.7M [00:00<00:00, 44.6MB/s]
- 24%|##3 | 10.6M/44.7M [00:00<00:01, 26.6MB/s]
- 36%|###5 | 16.0M/44.7M [00:00<00:00, 34.6MB/s]
- 54%|#####3 | 24.0M/44.7M [00:00<00:00, 42.3MB/s]
- 63%|######3 | 28.3M/44.7M [00:00<00:00, 38.3MB/s]
- 72%|#######2 | 32.2M/44.7M [00:00<00:00, 38.5MB/s]
- 93%|#########3| 41.6M/44.7M [00:01<00:00, 53.4MB/s]
-100%|##########| 44.7M/44.7M [00:01<00:00, 42.9MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 62.4MB/s]
+ 41%|#### | 18.2M/44.7M [00:00<00:00, 85.2MB/s]
+ 60%|#####9 | 26.6M/44.7M [00:00<00:00, 70.0MB/s]
+ 89%|########9 | 39.9M/44.7M [00:00<00:00, 92.9MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 78.6MB/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 99f625d82b..931207b7f3 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ 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 24.480 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.493 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 bde7d03e2d..d846d6fdab 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>06:31.545</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:25.242</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>01:24.480</p></td>
+<td><p>01:21.493</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>01:19.704</p></td>
+<td><p>01:16.673</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>00:52.730</p></td>
+<td><p>00:52.507</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>00:36.502</p></td>
+<td><p>00:36.958</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>00:30.966</p></td>
+<td><p>00:31.572</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>00:30.758</p></td>
+<td><p>00:29.987</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>00:26.295</p></td>
+<td><p>00:27.688</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>00:25.150</p></td>
+<td><p>00:24.254</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>00:22.293</p></td>
+<td><p>00:21.474</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>00:02.666</p></td>
+<td><p>00:02.635</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 cab65bf2a9..60043783ae 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2716.2963 2715.5848 2723.3126 2712.9677 3.0337
+ 2754.1907 2753.1235 2760.5896 2750.7188 3.2330
</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 7510f5f52e..d8b9021247 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2804 16.3079 16.7753 15.6254 0.4288
+ 15.5475 15.4613 16.2250 15.4136 0.2319
</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 98c6b95820..fb0d07efa2 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,33 +454,29 @@ 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 | 7.99M/170M [00:00<00:04, 39.5MB/s]
- 9%|9 | 16.0M/170M [00:00<00:03, 46.3MB/s]
- 13%|#3 | 22.3M/170M [00:00<00:03, 50.9MB/s]
- 16%|#6 | 27.4M/170M [00:00<00:03, 49.0MB/s]
- 19%|#8 | 32.1M/170M [00:00<00:03, 37.2MB/s]
- 24%|##3 | 40.2M/170M [00:00<00:02, 48.6MB/s]
- 27%|##7 | 46.3M/170M [00:01<00:02, 43.5MB/s]
- 30%|### | 51.0M/170M [00:01<00:02, 43.5MB/s]
- 36%|###5 | 60.7M/170M [00:01<00:01, 57.7MB/s]
- 39%|###9 | 66.8M/170M [00:01<00:02, 40.3MB/s]
- 44%|####3 | 74.0M/170M [00:01<00:02, 47.3MB/s]
- 47%|####6 | 79.7M/170M [00:01<00:01, 49.7MB/s]
- 50%|##### | 85.2M/170M [00:01<00:01, 50.2MB/s]
- 53%|#####3 | 90.6M/170M [00:02<00:04, 19.5MB/s]
- 57%|#####6 | 96.0M/170M [00:02<00:03, 22.4MB/s]
- 61%|######1 | 104M/170M [00:03<00:02, 27.6MB/s]
- 66%|######5 | 112M/170M [00:03<00:01, 34.9MB/s]
- 71%|####### | 120M/170M [00:03<00:01, 41.3MB/s]
- 74%|#######4 | 126M/170M [00:03<00:01, 43.5MB/s]
- 78%|#######7 | 132M/170M [00:03<00:00, 47.6MB/s]
- 81%|########1 | 138M/170M [00:03<00:00, 37.4MB/s]
- 86%|########5 | 146M/170M [00:03<00:00, 45.5MB/s]
- 89%|########9 | 152M/170M [00:03<00:00, 45.5MB/s]
- 93%|#########3| 158M/170M [00:04<00:00, 49.4MB/s]
- 96%|#########6| 164M/170M [00:04<00:00, 43.7MB/s]
- 99%|#########9| 168M/170M [00:04<00:00, 41.3MB/s]
-100%|##########| 170M/170M [00:04<00:00, 40.4MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 60.4MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:03, 42.5MB/s]
+ 11%|# | 18.6M/170M [00:00<00:03, 41.0MB/s]
+ 17%|#6 | 28.3M/170M [00:00<00:02, 59.7MB/s]
+ 20%|## | 34.5M/170M [00:00<00:02, 60.4MB/s]
+ 24%|##3 | 40.7M/170M [00:00<00:02, 61.2MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:02, 60.0MB/s]
+ 33%|###2 | 56.0M/170M [00:01<00:01, 60.3MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:01, 66.0MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 70.4MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 69.0MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 68.4MB/s]
+ 57%|#####6 | 96.8M/170M [00:01<00:01, 74.8MB/s]
+ 61%|######1 | 104M/170M [00:01<00:00, 69.0MB/s]
+ 66%|######5 | 112M/170M [00:01<00:00, 70.9MB/s]
+ 71%|####### | 120M/170M [00:02<00:00, 58.5MB/s]
+ 75%|#######5 | 128M/170M [00:02<00:00, 62.9MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 65.4MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 59.8MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 59.8MB/s]
+ 94%|#########4| 160M/170M [00:02<00:00, 64.8MB/s]
+ 99%|#########8| 168M/170M [00:02<00:00, 69.1MB/s]
+100%|##########| 170M/170M [00:02<00:00, 64.0MB/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=& [...]
@@ -578,7 +574,7 @@ 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 32.347 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 21.372 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 86ff93b51a..bffffd39e0 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,9 +495,9 @@ 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]
- 38%|###8 | 5.18M/13.6M [00:00<00:00, 32.3MB/s]
- 61%|###### | 8.26M/13.6M [00:00<00:00, 24.7MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 33.0MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 44.8MB/s]
+ 91%|######### | 12.3M/13.6M [00:00<00:00, 38.0MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 42.6MB/s]
</pre></div>
</div>
</div>
@@ -588,7 +588,7 @@ 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)
- 88.8169 88.7828 89.4389 88.6245 0.1510
+ 90.0147 89.9609 90.6130 89.8015 0.1830
</pre></div>
</div>
<div class="admonition note">
@@ -627,7 +627,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.722 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.374 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 4bb12180e4..e79d32e4af 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -580,7 +580,7 @@ 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)
- 117.8774 117.8101 124.2038 116.5215 0.9200
+ 116.7811 116.5945 123.2361 115.7550 0.9130
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ 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 25.758 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 25.213 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 172567ad96..747acd7ecc 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ 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 50.887 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 40.396 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 6a365e6482..bb611e4a2c 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,24 +463,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|3 | 5259/132723 [00:00<00:02, 52583.28KB/s]
- 10%|9 | 12773/132723 [00:00<00:01, 65846.94KB/s]
- 15%|#5 | 20367/132723 [00:00<00:01, 70442.11KB/s]
- 21%|##1 | 27971/132723 [00:00<00:01, 72648.16KB/s]
- 27%|##6 | 35540/132723 [00:00<00:01, 73738.49KB/s]
- 33%|###2 | 43156/132723 [00:00<00:01, 74557.36KB/s]
- 38%|###8 | 50781/132723 [00:00<00:01, 75107.45KB/s]
- 44%|####3 | 58293/132723 [00:00<00:00, 75108.85KB/s]
- 50%|####9 | 65825/132723 [00:00<00:00, 75172.35KB/s]
- 56%|#####5 | 73754/132723 [00:01<00:00, 76442.27KB/s]
- 61%|######1 | 81572/132723 [00:01<00:00, 76968.58KB/s]
- 67%|######7 | 89454/132723 [00:01<00:00, 77529.35KB/s]
- 73%|#######3 | 97445/132723 [00:01<00:00, 78246.59KB/s]
- 79%|#######9 | 105468/132723 [00:01<00:00, 78844.62KB/s]
- 85%|########5 | 113468/132723 [00:01<00:00, 79190.49KB/s]
- 92%|#########1| 121508/132723 [00:01<00:00, 79551.92KB/s]
- 98%|#########7| 129572/132723 [00:01<00:00, 79867.83KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 76297.77KB/s]
+ 5%|4 | 6186/132723 [00:00<00:02, 61841.63KB/s]
+ 11%|# | 14142/132723 [00:00<00:01, 72260.84KB/s]
+ 17%|#6 | 22210/132723 [00:00<00:01, 76100.20KB/s]
+ 23%|##2 | 30293/132723 [00:00<00:01, 77964.40KB/s]
+ 29%|##8 | 38229/132723 [00:00<00:01, 78463.74KB/s]
+ 35%|###4 | 46109/132723 [00:00<00:01, 78575.41KB/s]
+ 41%|#### | 54072/132723 [00:00<00:00, 78918.15KB/s]
+ 47%|####6 | 61964/132723 [00:00<00:00, 78763.99KB/s]
+ 53%|#####2 | 69897/132723 [00:00<00:00, 78939.60KB/s]
+ 59%|#####8 | 77792/132723 [00:01<00:00, 77819.03KB/s]
+ 64%|######4 | 85578/132723 [00:01<00:00, 77443.16KB/s]
+ 70%|####### | 93325/132723 [00:01<00:00, 77153.97KB/s]
+ 76%|#######6 | 101043/132723 [00:01<00:00, 77027.61KB/s]
+ 82%|########1 | 108747/132723 [00:01<00:00, 76913.75KB/s]
+ 88%|########7 | 116440/132723 [00:01<00:00, 76587.46KB/s]
+ 94%|#########3| 124101/132723 [00:01<00:00, 76589.19KB/s]
+ 99%|#########9| 131777/132723 [00:01<00:00, 76637.78KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 76994.32KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -519,7 +519,7 @@ 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 38.326 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 38.023 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 ff80e22358..0184281644 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>15:11.582</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:45.835</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_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>03:38.326</p></td>
+<td><p>03:38.023</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>03:32.347</p></td>
+<td><p>03:21.372</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>02:25.758</p></td>
+<td><p>02:25.213</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>01:50.887</p></td>
+<td><p>01:40.396</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:13.722</p></td>
+<td><p>01:12.374</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>00:55.774</p></td>
+<td><p>00:56.040</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>00:40.938</p></td>
+<td><p>00:39.783</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>00:27.173</p></td>
+<td><p>00:26.481</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>00:26.651</p></td>
+<td><p>00:26.145</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 908db5064d..604ac40395 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -619,7 +619,7 @@ 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.zip81f8bf3f-9b9e-4e3b-8d3a-a7f671a4c416 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.zipf828034c-cedd-4764-bee2-0f27631d164a 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 721c977f14..a97b0c1775 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>00:51.732</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:51.494</strong> total execution time for <strong>how_to_extend_tvm</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="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>00:48.030</p></td>
+<td><p>00:47.832</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>00:02.633</p></td>
+<td><p>00:02.613</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>00:01.061</p></td>
+<td><p>00:01.041</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index f440c05267..782d205ee8 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ 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: 20675us [20675us] (48.67%; 48.67%)
-FoldScaleAxis: 21805us [6us] (51.33%; 51.33%)
- FoldConstant: 21799us [1731us] (51.32%; 99.97%)
- InferType: 20068us [20068us] (47.24%; 92.06%)
+InferType: 20741us [20741us] (48.76%; 48.76%)
+FoldScaleAxis: 21795us [6us] (51.24%; 51.24%)
+ FoldConstant: 21789us [1657us] (51.22%; 99.97%)
+ InferType: 20131us [20131us] (47.33%; 92.39%)
</pre></div>
</div>
</div>
@@ -551,10 +551,10 @@ 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: 20037us [20037us] (48.28%; 48.28%)
-FoldScaleAxis: 21461us [5us] (51.72%; 51.72%)
- FoldConstant: 21456us [1652us] (51.70%; 99.98%)
- InferType: 19804us [19804us] (47.72%; 92.30%)
+InferType: 20398us [20398us] (48.52%; 48.52%)
+FoldScaleAxis: 21640us [5us] (51.48%; 51.48%)
+ FoldConstant: 21635us [1645us] (51.47%; 99.98%)
+ InferType: 19990us [19990us] (47.55%; 92.40%)
</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 02207380e8..662c0fb7b4 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -575,7 +575,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.103969 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 50.872032 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 6d92973b28..fa9f02465a 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -867,7 +867,7 @@ 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: 6.686000 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.009689 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 f144d60de6..2cc8290793 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -472,8 +472,8 @@ 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: 0.017782
-Baseline: 3.359834
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017636
+Baseline: 3.227152
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -532,7 +532,7 @@ 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: 0.299228
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.295510
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.328327
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.334643
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -644,7 +644,7 @@ 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: 0.113307
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.112489
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -721,7 +721,7 @@ 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: 0.108601
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108494
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
<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: 0.109748
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110456
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -879,7 +879,7 @@ class Module:
<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: 0.144683
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146283
</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 e886b559a1..76c75ee73e 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>00:34.318</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.087</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>00:31.769</p></td>
+<td><p>00:31.504</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>00:01.491</p></td>
+<td><p>00:01.512</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>00:01.058</p></td>
+<td><p>00:01.071</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 f9a433b7bf..9559629ac6 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>09:31.794</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:49.378</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>05:51.365</p></td>
+<td><p>06:08.157</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>01:37.827</p></td>
+<td><p>01:38.187</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>01:06.385</p></td>
+<td><p>01:06.315</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>00:29.180</p></td>
+<td><p>00:29.735</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>00:14.268</p></td>
+<td><p>00:14.248</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>00:12.769</p></td>
+<td><p>00:12.735</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 c9bafd568d..f50e662132 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
@@ -506,57 +506,956 @@ class Module:
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 128)
- conv2d_nchw = T.allocate([4], "float32", "local")
- pad_temp_shared = T.allocate([252], "float32", "shared")
- kernel_shared = T.allocate([48], "float32", "shared")
+ T.launch_thread(blockIdx_x, 64)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([2016], "float32", "shared")
+ kernel_shared = T.allocate([768], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 49)
+ T.launch_thread(threadIdx_x, 28)
conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(128, 3):
- cse_var_2: T.int32 = rc_outer_outer * 196
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer, ry_outer_outer in T.grid(16, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 1568
cse_var_1: T.int32 = ry_outer_outer * 7
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((252,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((2016,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 // 9 + ry_outer_outer and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + cse_var_1 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(1 <= (threadIdx_x_1 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 49) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(1 <= (threadIdx_x_1 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 147) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= (threadIdx_x_1 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + cse_var_1 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 49):
- if T.likely(threadIdx_x_1 < 7):
- pad_temp_shared_1[threadIdx_x_1 + 245] = T.if_then_else((threadIdx_x_1 + 56) // 9 + ry_outer_outer < 8 and threadIdx_x_1 < 6, data_1[cse_var_2 + (threadIdx_x_1 + 245) // 9 * 7 + cse_var_1 + threadIdx_x_1 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 56] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 56) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 57] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 57) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 112] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 112) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 113] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 113) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 168] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 168) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 169] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 169) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 224] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 224) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 225] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 167], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 280] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 280) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 281] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 281) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 336] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 336) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 337] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 337) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 392] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 392) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 393] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 393) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 448] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 448) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 449] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 449) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 504] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 384], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 505] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 505) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 560] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 560) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 561] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 561) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 616] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 616) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 617] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 617) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 672] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 672) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 673] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 673) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 728] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 728) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 729] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 559], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 784] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 784) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 785] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 785) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 840] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 840) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 841] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 841) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 896] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 896) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 897] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 897) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 952] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 952) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 953] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 953) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1008] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 776], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1009] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1009) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1064] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1064) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1065] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1065) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1120] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1120) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1121] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1121) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1176) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1177] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1177) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1232] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1232) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1233] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 951], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1288] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1288) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1289] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1289) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1344] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1344) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1345] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1345) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1400] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1400) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1401] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1401) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1456] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1456) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1457] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1457) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1512] = T.if_then_else(1 <= threadIdx_x_1 * 2 // 9 + ry_outer_outer and threadIdx_x_1 * 2 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 1168], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1513] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1513) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1568] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1568) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1569] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1569) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1624] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 49) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1624) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1625] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 50) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1625) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1680] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1680) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1681] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1681) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1736] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1736) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1737] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 2 % 9 and threadIdx_x_1 * 2 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 9 * 7 + cse_var_1 + threadIdx_x_1 * 2 % 9 + 1343], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1792] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 1) % 9 and (threadIdx_x_1 * 2 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1792) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1793] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 2) % 9 and (threadIdx_x_1 * 2 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1793) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1848] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 21) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 3) % 9 and (threadIdx_x_1 * 2 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1848) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1849] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 22) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 4) % 9 and (threadIdx_x_1 * 2 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1849) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1904] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 5) % 9 and (threadIdx_x_1 * 2 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1904) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1905] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 6) % 9 and (threadIdx_x_1 * 2 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1905) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 28):
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1960] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 7) % 9 and (threadIdx_x_1 * 2 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1960) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 2 + 1961] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 2 + 8) % 9 and (threadIdx_x_1 * 2 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1961) // 9 * 7 + cse_var_1 + (threadIdx_x_1 * 2 + 8) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((48,), data=kernel_shared, scope="shared")
- with T.launch_thread(threadIdx_x_2, 49):
- if T.likely(threadIdx_x_2 < 48):
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 12 * 4608 + rc_outer_outer * 36 + threadIdx_x_2 % 12 // 3 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
- for rc_outer_inner, rx_outer_inner in T.grid(2, 3):
- cse_var_3: T.int32 = rc_outer_inner * 6 + rx_outer_inner
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 24]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 27]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 36]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x // 7 * 9 + rx_outer_inner + threadIdx_x % 7 + 63] * kernel_shared_1[cse_var_3 + 39]
+ kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
+ with T.launch_thread(threadIdx_x_2, 28):
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + threadIdx_x_2 * 64 % 96 // 3 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 1] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 1) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 2] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 2) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 3] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 1) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 4] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 4) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 5] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 5) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 6] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 2) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 7] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 7) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 8] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 8) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 9] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 3) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 10] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 10) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 11] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 11) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 12] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 4) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 13] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 13) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 14] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 14) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 15] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 5) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 16] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 16) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 17] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 17) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 18] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 6) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 19] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 19) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 20] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 20) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 21] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 7) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 22] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 22) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 23] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 23) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 24] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 8) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 25] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 25) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 26] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 26) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 27] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 9) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 28] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 28) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 29] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 29) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 30] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 10) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 31] = kernel_1[blockIdx_x * 36864 + threadIdx_x_2 * 2 // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 31) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 32] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 32) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 33] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 11) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 34] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 34) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 35] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 35) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 36] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 12) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 37] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 37) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 38] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 38) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 39] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 13) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 40] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 40) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 41] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 41) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 42] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 14) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 43] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 43) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 44] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 44) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 45] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 15) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 46] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 46) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 47] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 47) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 48] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 16) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 49] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 49) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 50] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 50) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 51] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 17) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 52] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 52) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 53] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 53) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 54] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 18) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 55] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 55) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 56] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 56) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 57] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 19) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 58] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 58) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 59] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 59) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 60] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 20) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 61] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 61) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 1) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 62] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 + 62) % 96 // 3 * 9 + ry_outer_outer * 3 + (threadIdx_x_2 + 2) % 3]
+ if T.likely(threadIdx_x_2 < 12):
+ kernel_shared_1[threadIdx_x_2 * 64 + 63] = kernel_1[blockIdx_x * 36864 + (threadIdx_x_2 * 2 + 1) // 3 * 4608 + rc_outer_outer * 288 + (threadIdx_x_2 * 64 // 3 + 21) % 32 * 9 + ry_outer_outer * 3 + threadIdx_x_2 % 3]
+ for rc_outer_inner in range(2):
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 126] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 189] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 252] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 315] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 378] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 441] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 504] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 567] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 630] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 693] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 756] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 819] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 882] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 945] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 96]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 99]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 126] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 102]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 189] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 105]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 252] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 108]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 315] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 111]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 378] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 114]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 441] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 117]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 504] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 120]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 567] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 123]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 630] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 126]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 693] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 129]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 756] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 132]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 819] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 135]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 882] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 138]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 945] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 97]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 100]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 103]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 106]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 109]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 112]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 115]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 118]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 505] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 121]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 568] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 124]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 631] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 127]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 694] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 130]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 757] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 133]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 820] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 136]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 883] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 139]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 946] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 71] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 134] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 197] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 260] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 323] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 386] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 449] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 512] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 575] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 638] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 701] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 764] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 827] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 890] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 953] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 98]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 66] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 67] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 68] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 69] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 71] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 101]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 129] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 130] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 131] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 132] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 133] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 134] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 104]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 192] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 193] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 194] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 195] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 196] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 197] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 107]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 255] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 256] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 257] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 258] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 259] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 260] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 110]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 318] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 319] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 320] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 321] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 322] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 323] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 113]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 381] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 382] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 383] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 384] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 385] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 386] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 116]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 444] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 445] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 446] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 447] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 448] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 449] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 119]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 506] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 507] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 508] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 509] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 510] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 511] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 512] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 122]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 569] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 570] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 571] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 572] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 573] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 574] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 575] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 125]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 632] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 633] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 634] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 635] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 636] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 637] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 638] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 128]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 695] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 696] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 697] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 698] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 699] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 700] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 701] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 131]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 758] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 759] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 760] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 761] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 762] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 763] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 764] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 134]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 821] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 822] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 823] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 824] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 825] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 826] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 827] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 137]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 884] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 885] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 886] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 887] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 888] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 889] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 890] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 140]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 947] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 948] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 949] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 950] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 951] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 952] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 1008 + threadIdx_x % 7 * 9 + 953] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 48 + 143]
for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 4 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x + 98] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 4 + i1_inner + 2], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 1] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 2] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 3] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 4] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 5] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 392 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 6] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_1[blockIdx_x * 8 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -590,7 +1489,7 @@ class Module:
<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: 0.322 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.298 ms
</pre></div>
</div>
</div>
@@ -621,17 +1520,17 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=1)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
@@ -642,14 +1541,14 @@ 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=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -666,16 +1565,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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)
+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=64)
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=49)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=2)
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=49)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
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", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -693,46 +1592,976 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[252];
- __shared__ float kernel_shared[48];
+extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 49) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 147) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((((((int)threadIdx.x) + 56) / 9) + ry_outer_outer) < 8) && (((int)threadIdx.x) < 6)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 245) / 9) * 7)) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) * 2)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 56)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 57)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 57) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 112)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 113)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 168)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 169)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 169) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 224)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 225)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 167)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 280)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 281)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 281) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 336)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 337)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 392)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 393)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 448)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 449)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 504)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 505)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 505) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 560)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 561)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 561) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 616)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 617)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 617) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 672)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 673)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 673) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 728)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 729)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 559)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 784)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 785)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 840)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 841)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 841) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 896)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 897)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 897) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 952)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 953)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 953) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1008)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 776)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1009)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1009) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1064)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1065)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1065) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1120)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1121)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1121) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1177) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1232)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1233)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 951)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1288)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1289)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1289) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1344)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1345)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1345) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1400)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1401)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1401) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1456)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1457)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1457) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1512)] = (((((1 <= (((((int)threadIdx.x) * 2) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) * 2) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 1168)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1513)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 1) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1513) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1568)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1569)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1569) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1624)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1625)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1625) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1680)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1681)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1681) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1736)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1737)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 2) % 9)) + 1343)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1792)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1793)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 2) % 9))) && ((((((int)threadIdx.x) * 2) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1793) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1848)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 3) % 9))) && ((((((int)threadIdx.x) * 2) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1849)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1849) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1904)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1905)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1905) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1960)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 2) + 1961)] = (((((1 <= ((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) + 8) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1961) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[(((int)threadIdx.x) * 64)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
}
- if (((int)threadIdx.x) < 48) {
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 1)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 1) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 2)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 2) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 3)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 1) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 4)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 5)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 5) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 6)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 2) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 7)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 7) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 8)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 9)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 3) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 10)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 10) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 11)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 11) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 12)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 13)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 13) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 14)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 14) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 15)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 5) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 16)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 17)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 17) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 18)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 6) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 19)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 19) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 20)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 20) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 21)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 7) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 22)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 22) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 23)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 23) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 24)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 25)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 25) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 26)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 26) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 27)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 9) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 28)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 28) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 29)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 29) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 30)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 10) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 31)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 31) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 32)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 33)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 11) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 34)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 34) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 35)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 35) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 36)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 12) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 37)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 37) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 38)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 38) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 39)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 13) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 40)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 40) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 41)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 41) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 42)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 14) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 43)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 43) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 44)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 44) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 45)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 15) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 46)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 46) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 47)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 47) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 48)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 49) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 50)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 50) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 51)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 17) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 52)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 52) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 53)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 53) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 54)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 18) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 55)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 55) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 56)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 57)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 19) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 58)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 58) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 59)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 59) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 60)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 20) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 61)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 61) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 62)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) + 62) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 12) {
+ kernel_shared[((((int)threadIdx.x) * 64) + 63)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 64) / 3) + 21) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
}
__syncthreads();
for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 6) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 126) + ((((int)threadIdx.x) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((rc_outer_inner * 6) + rx_outer_inner) + 39)]));
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 631)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 694)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 757)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 820)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 883)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 946)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 507)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 508)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 509)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 510)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 570)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 571)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 572)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 573)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 632)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 633)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 634)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 635)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 636)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 695)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 696)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 697)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 698)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 699)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 758)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 759)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 760)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 761)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 762)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 821)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 822)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 823)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 824)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 825)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 884)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 885)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 886)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 887)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 888)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 947)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 948)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 949)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 950)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 951)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) % 7) * 9)) + 953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 48)) + 143)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -769,7 +2598,7 @@ 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 51.365 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 8.157 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 b6449be3d7..25acc55cd9 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ 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)
- 7.9244 7.9249 7.9365 7.9116 0.0102
+ 7.8829 7.8821 7.8860 7.8805 0.0023
</pre></div>
</div>
</div>
@@ -938,7 +938,7 @@ 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 6.385 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.315 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 9f87778b83..9052d51d9e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ 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)
- 738.6193 737.4406 742.1454 736.2720 2.5385
+ 750.4639 748.3697 754.7954 748.2266 3.0634
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ 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 37.827 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 38.187 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 95a95b5480..5308f7e4d8 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,27 +632,27 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer in T.parallel(8):
- compute_1 = T.allocate([64], "float32", "global")
- for i1_outer in range(128):
- compute_2 = T.Buffer((64,), data=compute_1)
- for i_inner_init, j_init in T.grid(16, 4):
- compute_2[i_inner_init * 4 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i1_outer // 4, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 16, 4):
+ for i0_outer_i1_outer_fused in T.parallel(64):
+ compute_1 = T.allocate([1024], "float32", "global")
+ compute_2 = T.Buffer((1024,), data=compute_1)
+ for i_outer_inner in range(2):
+ for i_inner_init, j_init in T.grid(32, 16):
+ compute_2[i_outer_inner * 512 + i_inner_init * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused % 32, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 32, 16):
cse_var_1 = T.var("int32")
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_2: T.int32 = i1_outer // 4
+ cse_var_2: T.int32 = i0_outer_i1_outer_fused % 32
if T.likely(elem_idx < placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]):
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- cse_var_3: T.int32 = i_inner * 4 + j
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + i1_outer % 4 * 4 + j] * T.max(placeholder_7[i0_outer * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
- for i0_inner in range(16):
- cse_var_4: T.int32 = i0_outer * 8192 + i0_inner * 512 + i1_outer * 4
- compute_3 = T.Buffer((65536,), data=compute.data)
- placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4:cse_var_4 + 4] = T.max(compute_2[i0_inner * 4:i0_inner * 4 + 4] + placeholder_5[cse_var_4:cse_var_4 + 4], T.Broadcast(T.float32(0), 4))
+ cse_var_3: T.int32 = i_outer_inner * 512 + i_inner * 16 + j
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_outer_inner * 8192 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
+ for i0_inner in range(64):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 32 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ compute_3[cse_var_4:cse_var_4 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_4:cse_var_4 + 16], T.Broadcast(T.float32(0), 16))
</pre></div>
</div>
</div>
@@ -686,7 +686,7 @@ class Module:
<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: 1.842 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.623 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 9b5d564d6f..aa14c512c8 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>00:52.416</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:38.135</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>00:52.384</p></td>
+<td><p>00:38.101</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>00:00.019</p></td>
+<td><p>00:00.022</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 cc11ddcc92..f2431de5ad 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -690,9 +690,29 @@ 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, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4412671
-No: 2 GFLOPS: 28.55/28.55 result: MeasureResult(costs=(0.008107613642857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.30165433883667, timestamp=1675732912.4704964) [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9293010
-No: 3 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9751699
+No: 2 GFLOPS: 3.17/3.17 result: MeasureResult(costs=(0.07312442775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.387472152709961, timestamp=1675748741.5792985) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3007064
+No: 3 GFLOPS: 0.00/3.17 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, 2, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7795425
+No: 4 GFLOPS: 31.14/31.14 result: MeasureResult(costs=(0.007434278714285715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.857502222061157, timestamp=1675748744.4044824) [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4713313
+No: 5 GFLOPS: 60.19/60.19 result: MeasureResult(costs=(0.003846041475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5972959995269775, timestamp=1675748747.2664506) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4744300
+No: 6 GFLOPS: 0.00/60.19 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
@@ -814,8 +834,8 @@ 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, 128, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7573571
-No: 4 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4921830
+No: 7 GFLOPS: 0.00/60.19 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
@@ -937,8 +957,8 @@ 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, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7753038
-No: 5 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10053592
+No: 8 GFLOPS: 0.00/60.19 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
@@ -1060,8 +1080,8 @@ 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, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6568056
-No: 6 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3340794
+No: 9 GFLOPS: 0.00/60.19 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
@@ -1183,9 +1203,8 @@ 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, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7928888
-No: 7 GFLOPS: 5.75/28.55 result: MeasureResult(costs=(0.0402826575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0895698070526123, timestamp=1675732916.6339478) [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5493417
-No: 8 GFLOPS: 0.00/28.55 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3301743
+No: 10 GFLOPS: 0.00/60.19 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
@@ -1307,9 +1326,8 @@ 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, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1204548
-No: 9 GFLOPS: 34.21/34.21 result: MeasureResult(costs=(0.00676794640909091,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0776684284210205, timestamp=1675732924.4722035) [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,68293
-No: 10 GFLOPS: 0.00/34.21 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10083541
+No: 11 GFLOPS: 0.00/60.19 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
@@ -1431,11 +1449,8 @@ 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, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8311525
-No: 11 GFLOPS: 40.97/40.97 result: MeasureResult(costs=(0.005650901333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4330289363861084, timestamp=1675732925.2379646) [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9394916
-No: 12 GFLOPS: 45.30/45.30 result: MeasureResult(costs=(0.005110728050000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.2402074337005615, timestamp=1675732925.9959552) [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8977051
-No: 13 GFLOPS: 18.14/45.30 result: MeasureResult(costs=(0.012761294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4122967720031738, timestamp=1675732937.180015) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('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', 1)],None,5699320
-No: 14 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8882606
+No: 12 GFLOPS: 0.00/60.19 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
@@ -1557,8 +1572,8 @@ 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, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6647285
-No: 15 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6033002
+No: 13 GFLOPS: 0.00/60.19 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
@@ -1680,26 +1695,8 @@ 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, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2861227
-No: 16 GFLOPS: 0.00/45.30 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, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9277896
-No: 17 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8311110
+No: 14 GFLOPS: 0.00/60.19 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
@@ -1821,8 +1818,8 @@ 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, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7584800
-No: 18 GFLOPS: 0.00/45.30 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, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4319686
+No: 15 GFLOPS: 0.00/60.19 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
@@ -1944,8 +1941,8 @@ 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, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8031143
-No: 19 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5982706
+No: 16 GFLOPS: 0.00/60.19 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
@@ -2067,8 +2064,9 @@ 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, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6714008
-No: 20 GFLOPS: 0.00/45.30 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7126835
+No: 17 GFLOPS: 63.28/63.28 result: MeasureResult(costs=(0.0036586410333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3199729919433594, timestamp=1675748750.9378455) [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,776724
+No: 18 GFLOPS: 0.00/63.28 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
@@ -2190,7 +2188,9 @@ 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, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7492272
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8931815
+No: 19 GFLOPS: 40.19/63.28 result: MeasureResult(costs=(0.005760213166666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9801359176635742, timestamp=1675748751.6873171) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7237241
+No: 20 GFLOPS: 30.99/63.28 result: MeasureResult(costs=(0.007470207714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9747631549835205, timestamp=1675748752.4501755) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9940581
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2229,9 +2229,9 @@ 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, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8977051
+[('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,776724
Finish loading 20 records
-Time cost of this operator: 0.005486
+Time cost of this operator: 0.003737
</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 fdd6a6fdbf..8befc4e459 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -643,10 +643,10 @@ 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 305.5 98.444 (1, 2, 10, 10, 3) 2 1 [305.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.782 1.219 (1, 6, 10, 10) 1 1 [3.782]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.047 0.337 (1, 1, 10, 10, 3) 1 1 [1.047]
-Total_time - 310.328 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 357.8 98.876 (1, 2, 10, 10, 3) 2 1 [357.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.111 0.86 (1, 6, 10, 10) 1 1 [3.111]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.264 (1, 1, 10, 10, 3) 1 1 [0.956]
+Total_time - 361.866 - - - - -
</pre></div>
</div>
</div>
@@ -698,10 +698,10 @@ 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 127.1 97.991 (1, 6, 10, 10, 1) 2 1 [127.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 1.362 (1, 6, 10, 10) 1 1 [1.767]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.839 0.647 (1, 3, 10, 10, 1) 1 1 [0.839]
-Total_time - 129.706 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.0 97.343 (1, 6, 10, 10, 1) 2 1 [100.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.704 (1, 6, 10, 10) 1 1 [1.75]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.979 0.953 (1, 1, 10, 10, 3) 1 1 [0.979]
+Total_time - 102.73 - - - - -
</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 c234dd402f..9e1b69c6e5 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -454,8 +454,7 @@ 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]
- 61%|###### | 2.09M/3.42M [00:00<00:00, 19.7MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 30.7MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 70.4MB/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.
@@ -581,7 +580,7 @@ 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 8.966 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.852 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 131595879f..a8cb0f0e24 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -523,7 +523,7 @@ 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/tmpdqejwjxp/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp1d07iyxf/images/random'
</pre></div>
</div>
</div>
@@ -583,8 +583,8 @@ 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], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [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/tmpdqejwjxp/images/target contains 8144 images
-/tmp/tmpdqejwjxp/images/random contains 5000 images
+<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], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [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/tmp1d07iyxf/images/target contains 8144 images
+/tmp/tmp1d07iyxf/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -696,13 +696,13 @@ 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 - 46s - loss: 0.2308 - accuracy: 0.9217 - val_loss: 0.1090 - val_accuracy: 0.9592 - 46s/epoch - 139ms/step
+328/328 - 47s - loss: 0.2308 - accuracy: 0.9170 - val_loss: 0.1005 - val_accuracy: 0.9630 - 47s/epoch - 142ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1020 - accuracy: 0.9628 - val_loss: 0.1442 - val_accuracy: 0.9494 - 43s/epoch - 130ms/step
+328/328 - 43s - loss: 0.1003 - accuracy: 0.9613 - val_loss: 0.0943 - val_accuracy: 0.9675 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 42s - loss: 0.0685 - accuracy: 0.9747 - val_loss: 0.0729 - val_accuracy: 0.9785 - 42s/epoch - 129ms/step
+328/328 - 43s - loss: 0.0679 - accuracy: 0.9748 - val_loss: 0.1147 - val_accuracy: 0.9626 - 43s/epoch - 130ms/step
-<keras.callbacks.History object at 0x7f672c502090>
+<keras.callbacks.History object at 0x7fb538580e90>
</pre></div>
</div>
</div>
@@ -966,7 +966,7 @@ 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 51.511 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 35.377 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 bf211af340..0ccf6a1690 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>07:04.781</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:49.992</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -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">5. 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>04:51.511</p></td>
+<td><p>04:35.377</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">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:08.966</p></td>
+<td><p>01:08.852</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">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:51.607</p></td>
+<td><p>00:52.699</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">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.729</p></td>
+<td><p>00:07.736</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">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:04.968</p></td>
+<td><p>00:05.328</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">7. Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index b7d5435e0e..20b8bc171c 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>00:43.616</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.474</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>00:31.831</p></td>
+<td><p>00:31.986</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>00:10.150</p></td>
+<td><p>00:10.728</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>00:01.629</p></td>
+<td><p>00:01.754</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 8309277a2e..b2fcbca12e 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 0x7f65d7cd0830>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fb3e39514d0>
</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 8c5dd7c8fb..dae085ec73 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>00:08.514</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.958</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>00:06.088</p></td>
+<td><p>00:04.216</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>00:01.076</p></td>
+<td><p>00:01.393</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>00:00.570</p></td>
+<td><p>00:00.572</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>00:00.553</p></td>
+<td><p>00:00.551</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>00:00.117</p></td>
+<td><p>00:00.114</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 5359f4943f..8e2eac7718 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ class Module:
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpaufvpqlw/input0.cc'\nsource_filename = \"/tmp/tmpaufvpqlw/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 [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpo4rpwrns/input0.cc'\nsource_filename = \"/tmp/tmpo4rpwrns/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 [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
</pre></div>
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 3c6a5ea361..fb19bd879d 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1616,7 +1616,7 @@ 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>
@@ -1900,7 +1900,7 @@ 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 1e87d9ef23..c1d67ec0ea 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/60fcb0ded/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 9f6b09142f..f744419898 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/60fcb0ded/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 13b4e7ae6e..45efbad1b9 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/60fcb0ded/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 c967d84e38..d556125283 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/60fcb0ded/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 26dd81b861..8d3991cdd4 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/60fcb0ded/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 56b8398861..d8261b71fd 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/60fcb0ded/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 e6b9d09d1f..824cf28645 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/60fcb0ded/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 6177f2c809..116cab2e06 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/60fcb0ded/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 7d72a7c809..8d524e8238 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/60fcb0ded/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 e8d7a5e523..d1d58b1f88 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/60fcb0ded/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 928757b2aa..7d8ab7e9a8 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/60fcb0ded/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 c0b616768f..97a8d89a36 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/60fcb0ded/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 53d2dc1299..89fed98fb9 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/60fcb0ded/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 a4eafb0f01..59ef8fadca 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/60fcb0ded/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 2784185da4..813aa25382 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/60fcb0ded/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/webgpu.ts#L172">webgpu.ts:172</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/60fcb0ded/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 f8ddec8a75..7a21d85730 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/60fcb0ded/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 c37b87b407..f8a1e6a058 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/60fcb0ded/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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/60fcb0ded/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/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 125aa4bdb7..21f0e8a89d 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/60fcb0ded/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 057e76b8df..d970526b41 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 282b8c0a45..91bdc49893 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 2dc0baf1dd..8f1ecc4023 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<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><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/60fcb0ded/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<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/60fcb0ded/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<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/60fcb0ded/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<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/60fcb0ded/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</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/60fcb0ded/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</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/60fcb0ded/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</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/60fcb0ded/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</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/60fcb0ded/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</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/60fcb0ded/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</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/60fcb0ded/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 8fbd8b1125..dc3fe34509 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<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">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 3e3fcbb1cd..9b128e7a25 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<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/60fcb0ded/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 9e5416cbce..0de98d4fff 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<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">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/60fcb0ded/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</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/60fcb0ded/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5456fae77/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 7e57ad319e..782d01afea 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 8e28d3f314..4ced3d1ff0 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:29.602</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:29.525</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:29.596</p></td>
+<td><p>00:29.519</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index a587c4ba10..5399a178d3 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -583,7 +583,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
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 31.64s!
+resnet18_v1 inference graph built in 31.32s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index f259916ec9..425f49b9fb 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -601,7 +601,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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 21.60s!
+yolov3-tiny inference graph built in 21.49s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 106d22e838..ab99355f54 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:36.504</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:36.723</strong> total execution time for <strong>topic_vta_tutorials_frontend</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="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.316</p></td>
+<td><p>00:48.541</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:48.188</p></td>
+<td><p>00:48.182</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index ee7cd4de72..97e5edf4dd 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.099</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.159</strong> total execution time for <strong>topic_vta_tutorials_optimize</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="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.648</p></td>
+<td><p>00:02.704</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.451</p></td>
+<td><p>00:00.455</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index fffdce61f5..cc2419bc80 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.757</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.764</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.391</p></td>
+<td><p>00:00.395</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.366</p></td>
+<td><p>00:00.369</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 7247327fa4..0c4c6e50fd 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -492,9 +492,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -572,7 +569,7 @@ class Module:
<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: 97.662 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 96.660 ms
</pre></div>
</div>
</div>
@@ -646,7 +643,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 44.694 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.703 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_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">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index f84ca5c328..4c9e8182ea 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -680,16 +680,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.90/0.90 result: MeasureResult(costs=(0.299862836,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.03689432144165, timestamp=1675731344.0013065) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
-No: 2 GFLOPS: 12.15/12.15 result: MeasureResult(costs=(0.0220975426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6425826549530029, timestamp=1675731344.6250105) [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
-No: 3 GFLOPS: 2.45/12.15 result: MeasureResult(costs=(0.10952323280000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9926838874816895, timestamp=1675731347.417639) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
-No: 4 GFLOPS: 11.58/12.15 result: MeasureResult(costs=(0.0231780338,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6277921199798584, timestamp=1675731348.833036) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
-No: 5 GFLOPS: 9.66/12.15 result: MeasureResult(costs=(0.0277882664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7126765251159668, timestamp=1675731349.6715972) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
-No: 6 GFLOPS: 3.26/12.15 result: MeasureResult(costs=(0.0822948214,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5707828998565674, timestamp=1675731352.0310268) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
-No: 7 GFLOPS: 13.11/13.11 result: MeasureResult(costs=(0.0204715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5757625102996826, timestamp=1675731352.6155608) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
-No: 8 GFLOPS: 1.63/13.11 result: MeasureResult(costs=(0.1642668912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8583526611328125, timestamp=1675731355.4997556) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
-No: 9 GFLOPS: 12.81/13.11 result: MeasureResult(costs=(0.0209598278,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6403548717498779, timestamp=1675731356.255377) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
-No: 10 GFLOPS: 2.12/13.11 result: MeasureResult(costs=(0.1263718674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2205970287323, timestamp=1675731358.5252938) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+No: 1 GFLOPS: 1.10/1.10 result: MeasureResult(costs=(0.2436254098,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.11844801902771, timestamp=1675747216.887491) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+No: 2 GFLOPS: 0.87/1.10 result: MeasureResult(costs=(0.3079831106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.148522853851318, timestamp=1675747222.0631766) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 3 GFLOPS: 8.70/8.70 result: MeasureResult(costs=(0.030843296400000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8636910915374756, timestamp=1675747223.547771) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+No: 4 GFLOPS: 2.72/8.70 result: MeasureResult(costs=(0.0985271742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8010296821594238, timestamp=1675747226.121015) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
+No: 5 GFLOPS: 3.66/8.70 result: MeasureResult(costs=(0.0732860996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4052789211273193, timestamp=1675747227.6757784) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+No: 6 GFLOPS: 2.44/8.70 result: MeasureResult(costs=(0.11006655800000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9935088157653809, timestamp=1675747229.6874518) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 7 GFLOPS: 3.93/8.70 result: MeasureResult(costs=(0.06836141300000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3519701957702637, timestamp=1675747231.779376) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+No: 8 GFLOPS: 2.60/8.70 result: MeasureResult(costs=(0.10330509380000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8996071815490723, timestamp=1675747233.6836398) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
+No: 9 GFLOPS: 1.51/8.70 result: MeasureResult(costs=(0.17792393899999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.047940969467163, timestamp=1675747236.8452926) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+No: 10 GFLOPS: 2.84/8.70 result: MeasureResult(costs=(0.0944473306,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7110950946807861, timestamp=1675747238.6050239) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 2320a27805..e637904232 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -558,7 +558,7 @@ standard deviation.</p>
<span class="nb">print</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">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 518.7866215400004, 'median': 518.8077074000034, 'std': 2.279827303963719}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 509.7426279499985, 'median': 509.1296362000037, 'std': 2.4044555332396995}
</pre></div>
</div>
</div>
@@ -710,176 +710,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 8.81/ 15.21 GFLOPS | Progress: (4/20) | 9.16 s
-[Task 1/25] Current/Best: 13.45/ 23.51 GFLOPS | Progress: (8/20) | 13.27 s
-[Task 1/25] Current/Best: 8.95/ 23.51 GFLOPS | Progress: (12/20) | 16.55 s
-[Task 1/25] Current/Best: 10.78/ 23.51 GFLOPS | Progress: (16/20) | 18.87 s
-[Task 1/25] Current/Best: 14.21/ 23.51 GFLOPS | Progress: (20/20) | 22.93 s Done.
+[Task 1/25] Current/Best: 9.56/ 22.61 GFLOPS | Progress: (4/20) | 8.95 s
+[Task 1/25] Current/Best: 9.69/ 22.61 GFLOPS | Progress: (8/20) | 15.86 s
+[Task 1/25] Current/Best: 11.24/ 22.61 GFLOPS | Progress: (12/20) | 18.47 s
+[Task 1/25] Current/Best: 8.57/ 23.55 GFLOPS | Progress: (16/20) | 20.53 s
+[Task 1/25] Current/Best: 12.32/ 23.55 GFLOPS | Progress: (20/20) | 23.60 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 14.90/ 21.68 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 2/25] Current/Best: 16.14/ 21.68 GFLOPS | Progress: (8/20) | 5.77 s
-[Task 2/25] Current/Best: 11.91/ 21.68 GFLOPS | Progress: (12/20) | 7.42 s
-[Task 2/25] Current/Best: 11.38/ 21.68 GFLOPS | Progress: (16/20) | 9.01 s
-[Task 2/25] Current/Best: 21.63/ 21.68 GFLOPS | Progress: (20/20) | 10.76 s Done.
... 533 lines suppressed ...