You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/11/03 01:25:56 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@ff6aaeb12ae71393fef37da8f9c72a0f2017e6d5)
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 5988fd3726 deploying docs (apache/tvm@ff6aaeb12ae71393fef37da8f9c72a0f2017e6d5)
5988fd3726 is described below
commit 5988fd3726f2b88bd014182cd1f3c9125ebb731a
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Nov 3 01:25:50 2022 +0000
deploying docs (apache/tvm@ff6aaeb12ae71393fef37da8f9c72a0f2017e6d5)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 314727 -> 302170 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23008 -> 22480 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_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2384 ++++++++++++--------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 86 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 672 +-----
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 46 +-
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 | 15 +-
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_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 43 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2384 ++++++++++++--------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 86 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 672 +-----
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 276 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 30 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
126 files changed, 3879 insertions(+), 4028 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 44d42e7073..2deab86823 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 979e8de9bd..9d8a85810f 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 b41829ed51..0dbfc5f575 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.278 seconds)
+ **Total running time of the script:** ( 1 minutes 14.441 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 48c296e981..dee7962695 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 989ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 980ms/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 bdce40e2e2..e5ad74add3 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6457ea1a-270a-4183-a2db-3d250161f548 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2aa13670-20ae-46b7-b08c-b23125a3ed99 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 23456cda76..bd1a2e2c3c 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 54.7MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 40.4MB/s]
44%|####4 | 18.3M/41.5M [00:00<00:00, 37.8MB/s]
57%|#####6 | 23.6M/41.5M [00:00<00:00, 42.8MB/s]
67%|######7 | 27.8M/41.5M [00:00<00:00, 36.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 32.8MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 32.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 35.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 60.5MB/s]
29%|##9 | 12.2M/41.5M [00:00<00:00, 61.1MB/s]
43%|####3 | 18.0M/41.5M [00:00<00:00, 43.4MB/s]
54%|#####4 | 22.6M/41.5M [00:00<00:00, 38.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.9MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 46.1MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 47.4MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 8fb8d8f505..5c2263228a 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 58.0MB/s]
33%|###3 | 14.8M/44.7M [00:00<00:00, 64.3MB/s]
48%|####8 | 21.6M/44.7M [00:00<00:00, 67.7MB/s]
63%|######3 | 28.2M/44.7M [00:00<00:00, 60.0MB/s]
76%|#######6 | 34.1M/44.7M [00:00<00:00, 46.4MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 46.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 56.6MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.30M/44.7M [00:00<00:00, 46.9MB/s]
24%|##4 | 10.8M/44.7M [00:00<00:00, 42.5MB/s]
44%|####3 | 19.5M/44.7M [00:00<00:00, 61.7MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 57.3MB/s]
83%|########2 | 37.1M/44.7M [00:00<00:00, 75.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 68.0MB/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 0f8dafa452..a07224fd78 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.360 seconds)
+ **Total running time of the script:** ( 1 minutes 12.819 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 794791e6eb..268394dd60 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:59.714** total execution time for **how_to_compile_models** files:
+**05:55.086** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:16.278 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:14.441 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.360 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.819 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:48.676 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.183 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.361 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.839 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.770 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.491 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.210 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.411 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.279 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.782 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.061 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.212 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.265 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.497 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.454 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.410 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 825589af75..49dfb191da 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
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 17.2892 16.6748 22.6245 16.2313 1.8203
+ 16.2720 16.1847 17.1205 16.1231 0.2844
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 28e1fb30e3..fe7560441d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:04, 36.0MB/s]
6%|5 | 9.74M/170M [00:00<00:05, 32.3MB/s]
9%|9 | 16.0M/170M [00:00<00:04, 35.1MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 44.7MB/s]
18%|#7 | 30.3M/170M [00:00<00:03, 48.3MB/s]
21%|## | 35.0M/170M [00:00<00:03, 43.9MB/s]
24%|##3 | 40.0M/170M [00:00<00:03, 43.7MB/s]
28%|##8 | 48.0M/170M [00:01<00:02, 46.7MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 48.4MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 47.8MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 53.8MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 56.9MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 49.9MB/s]
54%|#####3 | 91.2M/170M [00:02<00:01, 49.6MB/s]
57%|#####6 | 96.1M/170M [00:02<00:01, 42.4MB/s]
60%|###### | 102M/170M [00:02<00:01, 46.1MB/s]
63%|######2 | 107M/170M [00:02<00:01, 40.7MB/s
]
66%|######5 | 112M/170M [00:02<00:01, 43.1MB/s]
71%|####### | 120M/170M [00:02<00:01, 42.9MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 47.3MB/s]
80%|######## | 136M/170M [00:03<00:00, 50.0MB/s]
85%|########4 | 144M/170M [00:03<00:00, 46.9MB/s]
89%|########9 | 152M/170M [00:03<00:00, 49.3MB/s]
94%|#########4| 160M/170M [00:03<00:00, 47.6MB/s]
99%|#########8| 168M/170M [00:03<00:00, 54.3MB/s]
100%|##########| 170M/170M [00:03<00:00, 47.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
8%|8 | 14.3M/170M [00:00<00:01, 148MB/s]
17%|#6 | 28.4M/170M [00:00<00:01, 118MB/s]
24%|##3 | 40.0M/170M [00:00<00:01, 117MB/s]
30%|### | 51.3M/170M [00:00<00:01, 112MB/s]
37%|###6 | 62.3M/170M [00:00<00:01, 104MB/s]
43%|####2 | 72.4M/170M [00:00<00:01, 98.7MB/s]
52%|#####1 | 88.0M/170M [00:00<00:00, 105MB/s]
58%|#####7 | 98.0M/170M [00:00<00:00, 102MB/s]
63%|######3 | 108M/170M [00:01<00:00, 96.7MB/s]
71%|####### | 120M/170M [00:01<00:00, 101MB/s]
76%|#######6 | 130M/170M [00:01<00:00, 94.8MB/s]
85%|########4 | 144M/170M [00:01<00:00, 107MB/s]
91%|######### | 154M/170M [00:01<00:00, 88.9MB/s]
96%|#########6| 163M/170M [00:01<00:00, 82.9MB/s]
100%|##########| 170M/170M [00:01<00:00, 99.3MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 25.440 seconds)
+ **Total running time of the script:** ( 3 minutes 20.583 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 863c7ecb38..07d5cdd52a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 48.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 57.2MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
86%|########5 | 11.7M/13.6M [00:00<00:00, 122MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 118MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.5040 90.4217 91.2382 90.1251 0.2516
+ 90.3706 90.3013 93.3681 90.1156 0.3427
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.737 seconds)
+ **Total running time of the script:** ( 1 minutes 7.477 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 414da69a8b..c1cdd0357d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.4490 120.3405 122.6966 119.2738 0.5330
+ 120.0229 120.0081 124.9250 119.2927 0.5624
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 28.799 seconds)
+ **Total running time of the script:** ( 2 minutes 29.539 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 f328abaed3..0be2dbae45 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 42.468 seconds)
+ **Total running time of the script:** ( 1 minutes 41.425 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 b59248f8ba..289ccaa5d6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5262/132723 [00:00<00:02, 52609.26KB/s]
10%|# | 13726/132723 [00:00<00:01, 71434.50KB/s]
16%|#5 | 20870/132723 [00:00<00:01, 59857.38KB/s]
22%|##2 | 29345/132723 [00:00<00:01, 68650.48KB/s]
27%|##7 | 36427/132723 [00:00<00:01, 50649.96KB/s]
34%|###3 | 44834/132723 [00:00<00:01, 59310.02KB/s]
40%|#### | 53244/132723 [00:00<00:01, 66006.32KB/s]
47%|####6 | 61733/132723 [00:00<00:00, 71263.51KB/s]
53%|#####2 | 70255/132723 [00:01<00:00, 75233.62KB/s]
59%|#####9 | 78768/132723 [00:01<00:00, 78091.66KB/s]
66%|######5 | 87212/132723 [00:01<00:00, 79945.12KB/s]
72%|#######2 | 95708/132723 [00:01<00:00, 81418.72KB/s]
79%|#######8 | 104230/132723 [00:01<00:00, 82541.94KB/s]
85%|########4 | 112702/132723 [00:01<00:00, 83187.75KB/s]
91%|#########1| 121096/132723 [00:01<00:00, 55201.00KB/s]
98%|########
#7| 129624/132723 [00:01<00:00, 61813.24KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67544.26KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6453/132723 [00:00<00:01, 64521.45KB/s]
11%|# | 14409/132723 [00:00<00:01, 73361.45KB/s]
16%|#6 | 21746/132723 [00:00<00:02, 50473.22KB/s]
22%|##2 | 29674/132723 [00:00<00:01, 59390.71KB/s]
28%|##8 | 37622/132723 [00:00<00:01, 65551.19KB/s]
34%|###4 | 45513/132723 [00:00<00:01, 69615.75KB/s]
40%|#### | 53538/132723 [00:00<00:01, 72837.53KB/s]
46%|####6 | 61543/132723 [00:00<00:00, 75013.88KB/s]
52%|#####2 | 69597/132723 [00:00<00:00, 76677.68KB/s]
58%|#####8 | 77491/132723 [00:01<00:00, 77356.24KB/s]
64%|######4 | 85520/132723 [00:01<00:00, 78237.31KB/s]
70%|####### | 93521/132723 [00:01<00:00, 78766.17KB/s]
77%|#######6 | 101551/132723 [00:01<00:00, 79224.56KB/s]
83%|########2 | 109510/132723 [00:01<00:00, 78349.56KB/s]
88%|########8 | 117447/132723 [00:01<00:00, 78649.70KB/s]
95%|########
#4| 125449/132723 [00:01<00:00, 79056.65KB/s]
100%|##########| 132723/132723 [00:01<00:00, 73940.69KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 7.496 seconds)
+ **Total running time of the script:** ( 3 minutes 3.561 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 5276afd9a2..4db1413d3e 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**13:22.086** total execution time for **how_to_deploy_models** files:
+**13:11.600** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:25.440 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:20.583 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:07.496 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:03.561 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.799 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:29.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.468 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:41.425 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.737 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.477 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:37.605 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.987 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.722 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.359 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.812 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.661 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index f315a3a422..7facfcdef2 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipd8ea5ee0-8ad0-45bb-aa4c-ccdd5fd695f7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8399a51e-0b6d-4b1e-90f9-41682026ce8e 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 4599fed5af..0b0add7d38 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
=================
-**00:48.636** total execution time for **how_to_extend_tvm** files:
+**00:47.916** 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``) | 00:45.058 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.351 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.498 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.479 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.072 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.079 | 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 529f9e33bf..bf032964c8 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6997us [6997us] (45.83%; 45.83%)
- FoldScaleAxis: 8269us [8us] (54.17%; 54.17%)
- FoldConstant: 8261us [1609us] (54.12%; 99.90%)
- InferType: 6653us [6653us] (43.58%; 80.53%)
+ InferType: 6838us [6838us] (46.19%; 46.19%)
+ FoldScaleAxis: 7967us [6us] (53.81%; 53.81%)
+ FoldConstant: 7962us [1631us] (53.77%; 99.93%)
+ InferType: 6331us [6331us] (42.76%; 79.52%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6795us [6795us] (40.12%; 40.12%)
- FoldScaleAxis: 10140us [8us] (59.88%; 59.88%)
- FoldConstant: 10133us [1682us] (59.83%; 99.92%)
- InferType: 8451us [8451us] (49.90%; 83.40%)
+ InferType: 6567us [6567us] (45.17%; 45.17%)
+ FoldScaleAxis: 7970us [6us] (54.83%; 54.83%)
+ FoldConstant: 7964us [1671us] (54.79%; 99.93%)
+ InferType: 6294us [6294us] (43.30%; 79.02%)
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 e22e8d3128..b81a6defc3 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.237728 ms
+ Convolution: 36.486686 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 ba83462d16..785e387f63 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
@@ -659,7 +659,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.378775 ms
+ conv2d with tensor core: 13.350697 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 fda8703d78..26f685751c 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019544
- Baseline: 3.365354
+ Numpy running time: 0.019089
+ Baseline: 3.422495
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.331463
+ Opt1: 0.326122
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.348065
+ Opt2: 0.349573
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.126888
+ Opt3: 0.122556
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110085
+ Opt4: 0.110757
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111257
+ Opt5: 0.111784
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.148202
+ Opt6: 0.148735
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 26ac31ae12..e127540ba4 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.551** total execution time for **how_to_optimize_operators** files:
+**00:35.749** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.080 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.455 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.538 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.091 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.130 | 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 22007b47b1..02d37a9065 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
=================
-**08:55.132** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:57.778** 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``) | 05:23.556 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:24.912 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:34.746 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:34.824 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.744 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.081 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.092 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.298 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.446 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.220 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.549 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.442 | 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 62b01976ba..3d658c7dd6 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,482 +240,781 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
+ let cse_var_1: int32 = (rc.outer.outer*392)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 14)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 14), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 28)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 28), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 42)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 6), 9)) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 42), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 70)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 70), 81)) && (floormod((threadIdx.x_1 + 70), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 70), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 84)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 84), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 126)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 126), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 5)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 140)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 140), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 154)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 73), 81)) && (floormod((threadIdx.x_1 + 73), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 154), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 73), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 182)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 182), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 210)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 210), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((threadIdx.x_1 < 10) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 238)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 238), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 252)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 252), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 1)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 266)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 266), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 6), 9)) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 308)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 308), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 322)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 322), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 350)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 350), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 26), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 364)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 364), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 40), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 378)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 378), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 6)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 406)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 1), 81)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 406), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 420)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 6), 9)) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 420), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 15), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 434)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 434), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 462)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 462), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 57), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 476)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 71), 81)) && (floormod((threadIdx.x_1 + 71), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 476), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 71), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 518)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 518), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 532)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 532), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 546)] = @tir.if_then_else((((threadIdx.x_1 < 12) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 546), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 574)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 7), 81)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 574), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 7), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 602)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 602), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 630)] = @tir.if_then_else((((threadIdx.x_1 < 9) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 630), 81)*49)) + threadIdx.x_1) + 41)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 644)] = 0f32
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14 {
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope="shared")[(threadIdx.x_2*48)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*16), 24), 3)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 1)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*16), 24), 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 2)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*16), 24), 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 3)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 4)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 5)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 6)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 7)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 8)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 9)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 10)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 11)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 12)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 13)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 14)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 15)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 16)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 17)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 18)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 19)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 20)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 21)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 22)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 23)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 24)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 25)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 26)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 27)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 28)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 29)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 30)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 31)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 32)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 33)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 34)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 35)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 36)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 37)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 38)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 39)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 40)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 41)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 42)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 43)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 44)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 45)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 46)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 47)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*196) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*4) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -771,7 +1070,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.363 ms
+ Execution time of this operator: 0.287 ms
@@ -819,36 +1118,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
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_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
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_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -866,14 +1165,14 @@ 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=48)
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=64)
+ 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=14)
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=4)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ 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=14)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -893,429 +1192,730 @@ 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__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(14) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[288];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 14)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 14) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 28)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 28) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 42)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 42) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 70)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 70) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 84)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 84) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 126)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 126) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 140)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 140) / 81) * 49)) + (((((int)threadIdx.x) + 59) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 154)] = (((((9 <= ((((int)threadIdx.x) + 73) % 81)) && (((((int)threadIdx.x) + 73) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 154) / 81) * 49)) + ((((((int)threadIdx.x) + 73) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 182)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 182) / 81) * 49)) + (((((int)threadIdx.x) + 20) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 196) / 81) * 49)) + (((((int)threadIdx.x) + 34) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 210)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 210) / 81) * 49)) + (((((int)threadIdx.x) + 48) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((int)threadIdx.x) < 10) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + (((((int)threadIdx.x) + 62) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 238)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 238) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 252)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 252) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 266)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 266) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 294) / 81) * 49)) + (((((int)threadIdx.x) + 51) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 308)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 308) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 322)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 322) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 350)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 350) / 81) * 49)) + (((((int)threadIdx.x) + 26) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 364)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 364) / 81) * 49)) + (((((int)threadIdx.x) + 40) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 378)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 378) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 34)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 406)] = ((((8 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 406) / 81) * 49)) + (((((int)threadIdx.x) + 1) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 420)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 420) / 81) * 49)) + (((((int)threadIdx.x) + 15) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 434)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 434) / 81) * 49)) + (((((int)threadIdx.x) + 29) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + (((((int)threadIdx.x) + 43) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 462)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 462) / 81) * 49)) + (((((int)threadIdx.x) + 57) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 476)] = (((((9 <= ((((int)threadIdx.x) + 71) % 81)) && (((((int)threadIdx.x) + 71) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 476) / 81) * 49)) + ((((((int)threadIdx.x) + 71) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 518)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 518) / 81) * 49)) + (((((int)threadIdx.x) + 32) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 532)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 532) / 81) * 49)) + (((((int)threadIdx.x) + 46) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 546)] = ((((((int)threadIdx.x) < 12) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 546) / 81) * 49)) + (((((int)threadIdx.x) + 60) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 574)] = ((((2 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 574) / 81) * 49)) + (((((int)threadIdx.x) + 7) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 602)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 602) / 81) * 49)) + (((((int)threadIdx.x) + 35) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + (((((int)threadIdx.x) + 49) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 630)] = ((((((int)threadIdx.x) < 9) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 630) / 81) * 49)) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 4) {
+ pad_temp_shared[(((int)threadIdx.x) + 644)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[(((int)threadIdx.x) * 48)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 16) % 24) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 1)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 16) % 24) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 2)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 16) % 24) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 3)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 1) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 4)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 1) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 5)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 1) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 6)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 2) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 7)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 2) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 8)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 2) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 9)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 10)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 11)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 12)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 4) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 13)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 4) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 14)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 4) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 15)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 5) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 16)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 5) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 17)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 5) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 18)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 2) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 19)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 2) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 20)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 2) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 21)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 7) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 22)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 7) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 23)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 7) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 24)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 8) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 25)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 8) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 26)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 8) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 27)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 3) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 28)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 3) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 29)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 3) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 30)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 10) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 31)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 10) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 32)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 10) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 33)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 11) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 34)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 11) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 35)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 11) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 36)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 4) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 37)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 4) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 38)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 4) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 39)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 13) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 40)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 13) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 41)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 13) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 42)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 14) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 43)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 14) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 44)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 14) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 45)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 5) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 46)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 5) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 47)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 5) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 4) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1378,7 +1978,7 @@ 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 23.556 seconds)
+ **Total running time of the script:** ( 5 minutes 24.912 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 271ad88776..b983543a82 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1967 8.2001 8.2046 8.1852 0.0083
+ 8.2192 8.2236 8.2315 8.2025 0.0122
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.744 seconds)
+ **Total running time of the script:** ( 1 minutes 4.081 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 a4a7005d75..4f205f579b 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 775.0565 775.0243 775.8859 774.2594 0.6644
+ 770.8568 771.4724 773.2872 767.8109 2.2777
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 34.746 seconds)
+ **Total running time of the script:** ( 1 minutes 34.824 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 2c536ec44c..62c5dd9d8f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,78 +386,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 1024) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [128], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2)
+ let cse_var_2: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 64)*2048) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_5: int32 = floormod(i0.outer.i1.outer.fused, 64)
+ let cse_var_6: int32 = (cse_var_5*8)
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 64)*4096) + (i0.inner*512)) + cse_var_6)
+ compute[ramp(cse_var_4, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_6) - (floordiv(cse_var_5, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_4, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -513,7 +465,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.717 ms
+ Execution time of this operator: 2.538 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 4bd12d4d28..98af17af08 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:28.691** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.365** 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``) | 00:28.655 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.329 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 a7901021ee..4a604e66d6 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -387,8 +387,11 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10018948
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1347833
+ No: 2 GFLOPS: 27.77/27.77 result: MeasureResult(costs=(0.008337656,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.136690855026245, timestamp=1667434045.462885) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2325325
+ No: 3 GFLOPS: 259.24/259.24 result: MeasureResult(costs=(0.000893015107142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.93196702003479, timestamp=1667434047.2434297) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3558974
+ No: 4 GFLOPS: 11.30/259.24 result: MeasureResult(costs=(0.020484367333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.858165502548218, timestamp=1667434048.9672313) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3544529
+ No: 5 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -510,9 +513,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2864213
- No: 3 GFLOPS: 10.07/10.07 result: MeasureResult(costs=(0.02298654933333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.742173433303833, timestamp=1667424787.0472581) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5918884
- No: 4 GFLOPS: 0.00/10.07 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9866393
+ No: 6 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -634,9 +636,13 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6114494
- No: 5 GFLOPS: 17.37/17.37 result: MeasureResult(costs=(0.013326816111111112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.785916328430176, timestamp=1667424792.0364811) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3174125
- No: 6 GFLOPS: 0.00/17.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5574085
+ No: 7 GFLOPS: 18.27/259.24 result: MeasureResult(costs=(0.012669486272727272,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.958767414093018, timestamp=1667434056.0623786) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8596967
+ No: 8 GFLOPS: 41.34/259.24 result: MeasureResult(costs=(0.005600369722222223,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.537811517715454, timestamp=1667434056.761774) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2517863
+ No: 9 GFLOPS: 8.37/259.24 result: MeasureResult(costs=(0.027643880750000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.271986484527588, timestamp=1667434066.119886) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8219272
+ No: 10 GFLOPS: 3.63/259.24 result: MeasureResult(costs=(0.0637336005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.639305830001831, timestamp=1667434067.3300345) [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9688708
+ No: 11 GFLOPS: 232.03/259.24 result: MeasureResult(costs=(0.0009977095940594059,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.32674503326416, timestamp=1667434067.9675095) [('tile_f', [-1, 1, 16, 8]), ('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, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9361158
+ No: 12 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -758,8 +764,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5532106
- No: 7 GFLOPS: 0.00/17.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3345506
+ No: 13 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -881,9 +887,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,885080
- No: 8 GFLOPS: 119.94/119.94 result: MeasureResult(costs=(0.0019302159807692307,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1279845237731934, timestamp=1667424794.7434168) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3293114
- No: 9 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,542252
+ No: 14 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1005,8 +1010,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2764456
- No: 10 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9260437
+ No: 15 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1128,8 +1133,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2351882
- No: 11 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4254013
+ No: 16 GFLOPS: 65.45/259.24 result: MeasureResult(costs=(0.003537009655172414,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3549180030822754, timestamp=1667434069.558425) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1451278
+ No: 17 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1251,8 +1257,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7916676
- No: 12 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,526536
+ No: 18 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1374,8 +1380,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2901850
- No: 13 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8255852
+ No: 19 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1497,624 +1503,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10296317
- No: 14 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4606271
- No: 15 GFLOPS: 2.48/119.94 result: MeasureResult(costs=(0.093395912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.356995105743408, timestamp=1667424797.5311258) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,508434
- No: 16 GFLOPS: 403.73/403.73 result: MeasureResult(costs=(0.0005734048857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.129640817642212, timestamp=1667424798.1717036) [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2013011
- No: 17 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2597932
- No: 18 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3377019
- No: 19 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4622637
- No: 20 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9482753
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2489652
+ No: 20 GFLOPS: 119.08/259.24 result: MeasureResult(costs=(0.0019440998103448276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1154589653015137, timestamp=1667434071.932883) [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8947438
@@ -2169,9 +1559,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2013011
+ [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3558974
Finish loading 20 records
- Time cost of this operator: 0.000986
+ Time cost of this operator: 0.001260
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 7f8e9bb48b..18d09c69cc 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
@@ -327,10 +327,10 @@ 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 311.8 98.718 (1, 2, 10, 10, 3) 2 1 [311.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.087 0.977 (1, 6, 10, 10) 1 1 [3.087]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.304 (1, 1, 10, 10, 3) 1 1 [0.961]
- Total_time - 315.848 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.5 98.725 (1, 2, 10, 10, 3) 2 1 [312.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.961 (1, 6, 10, 10) 1 1 [3.042]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.994 0.314 (1, 1, 10, 10, 3) 1 1 [0.994]
+ Total_time - 316.536 - - - - -
@@ -394,10 +394,10 @@ 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 100.1 97.11 (1, 6, 10, 10, 1) 2 1 [100.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.002 1.942 (1, 6, 10, 10) 1 1 [2.002]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.948 (1, 1, 10, 10, 3) 1 1 [0.978]
- Total_time - 103.079 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.3 97.432 (1, 6, 10, 10, 1) 2 1 [103.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.669 (1, 6, 10, 10) 1 1 [1.77]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.899 (1, 1, 10, 10, 3) 1 1 [0.953]
+ Total_time - 106.023 - - - - -
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 3a52ec42cf..79c023db6a 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpr703tk5r/images/random'
+ '/tmp/tmp_he_bkvt/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [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], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpr703tk5r/images/target contains 8144 images
- /tmp/tmpr703tk5r/images/random contains 5000 images
+ /tmp/tmp_he_bkvt/images/target contains 8144 images
+ /tmp/tmp_he_bkvt/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2159 - accuracy: 0.9237 - val_loss: 0.2209 - val_accuracy: 0.9256 - 47s/epoch - 144ms/step
+ 328/328 - 47s - loss: 0.2151 - accuracy: 0.9280 - val_loss: 0.1232 - val_accuracy: 0.9520 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0994 - accuracy: 0.9605 - val_loss: 0.1332 - val_accuracy: 0.9562 - 44s/epoch - 134ms/step
+ 328/328 - 44s - loss: 0.0990 - accuracy: 0.9645 - val_loss: 0.1204 - val_accuracy: 0.9585 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0737 - accuracy: 0.9708 - val_loss: 0.1085 - val_accuracy: 0.9660 - 44s/epoch - 134ms/step
+ 328/328 - 43s - loss: 0.0641 - accuracy: 0.9764 - val_loss: 0.1628 - val_accuracy: 0.9592 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f697c4cf650>
+ <keras.callbacks.History object at 0x7fcde4465990>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 41.437 seconds)
+ **Total running time of the script:** ( 5 minutes 4.899 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 2ae40bfc03..e35a5247bd 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**05:45.808** total execution time for **how_to_work_with_microtvm** files:
+**06:07.992** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:41.437 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:04.899 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.827 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.811 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.624 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.442 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.917 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.838 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 1c775ffd68..3d7e0142f1 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:45.253** total execution time for **how_to_work_with_relay** files:
+**00:43.900** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.090 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.487 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.869 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.626 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.537 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 1f06c762d4..7a29afd9d1 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f692599ab00>
+ <function my_cuda_math_rule at 0x7fcd855175f0>
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 775533966c..e10e0d2f03 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
@@ -5,20 +5,20 @@
Computation times
=================
-**00:06.511** total execution time for **how_to_work_with_schedules** files:
+**00:08.366** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.082 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.070 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.062 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.959 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.583 | 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``) | 00:00.567 | 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``) | 00:00.118 | 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_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 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 9a9a2f98e2..39a9b76051 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpnddzkjp_/input0.cc'\nsource_filename = \"/tmp/tmpnddzkjp_/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpvharewve/input0.cc'\nsource_filename = \"/tmp/tmpvharewve/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index facb870913..caf9000eb6 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:27.019** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.986** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.013 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.980 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 6b0f46a694..211d67e18a 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 30.38s!
+ resnet18_v1 inference graph built in 30.01s!
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 b33f2f4046..7379be57c9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 20.21s!
+ yolov3-tiny inference graph built in 20.15s!
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 a7bd845af2..90d3983133 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:42.937** total execution time for **topic_vta_tutorials_frontend** files:
+**01:42.791** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.421 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.899 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.516 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.891 | 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 ea13c65c0b..ba786c5f50 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
=================
-**00:03.195** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.227** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.726 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.778 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.468 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.449 | 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 314f2c1564..d0741d109c 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
=================
-**00:00.808** total execution time for **topic_vta_tutorials** files:
+**00:00.779** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.430 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.413 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.378 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.366 | 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 e57e111c57..88600504e7 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -333,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 98.192 ms
+ Execution time of this operator: 93.755 ms
@@ -451,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 35.173 seconds)
+ **Total running time of the script:** ( 1 minutes 10.817 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 5bf8bdda13..b8bcfd4c11 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 12.72/12.72 result: MeasureResult(costs=(0.0211104258,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4818730354309082, timestamp=1667423365.9778728) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
- No: 2 GFLOPS: 9.71/12.72 result: MeasureResult(costs=(0.027633449999999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6712994575500488, timestamp=1667423366.626273) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 3 GFLOPS: 13.41/13.41 result: MeasureResult(costs=(0.020021107599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4986720085144043, timestamp=1667423367.883513) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
- No: 4 GFLOPS: 11.52/13.41 result: MeasureResult(costs=(0.023311126999999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5251164436340332, timestamp=1667423369.1974487) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
- No: 5 GFLOPS: 8.41/13.41 result: MeasureResult(costs=(0.0319151988,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7173418998718262, timestamp=1667423370.0715425) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
- No: 6 GFLOPS: 12.83/13.41 result: MeasureResult(costs=(0.020920360800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5095353126525879, timestamp=1667423370.5774202) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
- No: 7 GFLOPS: 2.87/13.41 result: MeasureResult(costs=(0.0933804018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6597132682800293, timestamp=1667423373.002721) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
- No: 8 GFLOPS: 9.49/13.41 result: MeasureResult(costs=(0.0282860752,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7388801574707031, timestamp=1667423373.6761277) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
- No: 9 GFLOPS: 12.43/13.41 result: MeasureResult(costs=(0.0215988132,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4922330379486084, timestamp=1667423374.2834795) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
- No: 10 GFLOPS: 2.31/13.41 result: MeasureResult(costs=(0.1161844804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9881327152252197, timestamp=1667423376.3064437) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+ No: 1 GFLOPS: 13.60/13.60 result: MeasureResult(costs=(0.0197373426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5104551315307617, timestamp=1667432658.6843472) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
+ No: 2 GFLOPS: 11.42/13.60 result: MeasureResult(costs=(0.0235155684,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.577028751373291, timestamp=1667432659.2727263) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+ No: 3 GFLOPS: 10.59/13.60 result: MeasureResult(costs=(0.025342561799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5496485233306885, timestamp=1667432660.6083689) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 4 GFLOPS: 11.64/13.60 result: MeasureResult(costs=(0.0230619778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5516703128814697, timestamp=1667432661.146751) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+ No: 5 GFLOPS: 12.26/13.60 result: MeasureResult(costs=(0.0218990796,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5174016952514648, timestamp=1667432661.781519) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
+ No: 6 GFLOPS: 8.73/13.60 result: MeasureResult(costs=(0.0307457902,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.646397590637207, timestamp=1667432663.211196) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
+ No: 7 GFLOPS: 9.44/13.60 result: MeasureResult(costs=(0.028443617799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6075448989868164, timestamp=1667432664.589291) [('tile_y', [-1, 2]), ('tile_x', [-1, 32])],None,51
+ No: 8 GFLOPS: 3.39/13.60 result: MeasureResult(costs=(0.07925548439999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.45725679397583, timestamp=1667432666.060041) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
+ No: 9 GFLOPS: 1.17/13.60 result: MeasureResult(costs=(0.22880944100000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7899985313415527, timestamp=1667432669.9658153) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 10 GFLOPS: 2.00/13.60 result: MeasureResult(costs=(0.1339585276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.261655807495117, timestamp=1667432672.2727134) [('tile_y', [-1, 8]), ('tile_x', [-1, 2])],None,13
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 61b724a8f7..719506c794 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 519.4300110699987, 'median': 519.3191480999758, 'std': 2.1550682887027333}
+ {'mean': 522.3170279700014, 'median': 521.8688147500018, 'std': 2.37780837536643}
@@ -554,30 +554,30 @@ 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: 9.30/ 13.06 GFLOPS | Progress: (4/20) | 8.92 s
[Task 1/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 10.80 s
[Task 1/25] Current/Best: 11.29/ 23.46 GFLOPS | Progress: (12/20) | 13.69 s
[Task 1/25] Current/Best: 16.83/ 23.46 GFLOPS | Progress: (16/20) | 17.97 s
[Task 1/25] Current/Best: 18.35/ 23.46 GFLOPS | Progress: (20/20) | 19.81 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.23/ 17.35 GFLOPS | Progress: (4/20) | 3.24 s
[Task 2/25] Current/Best: 20.11/ 20.11 GFLOPS | Progress: (8/20) | 4.80 s
[Task 2/25] Current/Best: 10.51/ 20.11 GFLOPS | Progress: (12/20) | 6.16 s
[Task 2/25] Current/Best: 5.65/ 20.11 GFLOPS | Progress: (16/20) | 7.31 s
[Task 2/25] Current/Best: 13.41/ 20.11 GFLOPS | Progress: (20/20) | 9.05 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.08/ 20.13 GFLOPS | Progress: (4/20) | 3.53 s
[Task 3/25] Current/Best: 12.54/ 20.13 GFLOPS | Progress: (8/20) | 6.02 s
[Task 3/25] Current/Best: 5.71/ 20.13 GFLOPS | Progress: (12/20) | 8.33 s
[Task 3/25] Current/Best: 9.36/ 22.50 GFLOPS | Progress: (16/20) | 10.65 s
[Task 3/25] Current/Best: 12.79/ 22.50 GFLOPS | Progress: (20/20) | 12.70 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.79/ 19.20 GFLOPS | Progress: (4/20) | 3.29 s
[Task 4/25] Current/Best: 11.42/ 19.20 GFLOPS | Progress: (8/20) | 5.94 s
[Task 4/25] Current/Best: 5.25/ 19.20 GFLOPS | Progress: (12/20) | 9.96 s
[Task 4/25] Current/Best: 11.08/ 19.20 GFLOPS | Progress: (16/20) | 13.58 s
[Task 4/25] Current/Best: 14.99/ 19.20 GFLOPS | Progress: (20/20) | 15.04 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 8.52/ 13.90 GFLOPS | Progress: (4/20) | 3.39 s
[Task 5/25] Current/Best: 3.46/ 14.23 GFLOPS | Progress: (8/20) | 5.59 s
[Task 5/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (12/20) | 7.26 s
[Task 5/25] Current/Best: 3.06/ 20.43 GFLOPS | Progress: (16/20) | 9.31 s
[Task 5/25] Current/Best: 14.63/ 21.52 GFLOPS | Progress: (20/20) | 11.38 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.95/ 18.01 GFLOPS | Progress: (4/20) | 4.88 s
[Task 6/25] Current/Best: 14.02/ 18.01 GFLOPS | Progress: (8/20) | 7.93 s
[Task 6/25] Current/Best: 13.37/ 18.01 GFLOPS | Progress: (12/20) | 10.41 s
[Task 6/25] Current/Best: 10.07/ 18.01 GFLOPS | Progress: (16/20) | 12.76 s
[Task 6/25] Current/Best: 13.31/ 18.01 GFLOPS | Progress: (20/20) | 14.96 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.62/ 16.62 GFLOPS | Progress: (4/20) | 3.71 s
[Task 7/25] Current/Best: 19.49/ 19.49 GFLOPS | Progress: (8/20) | 6.16 s
[Task 7/25] Current/Best: 13.40/ 19.49 GFLOPS | Progress: (12/20) | 8.06 s
[Task 7/25] Current/Best: 12.12/ 19.49 GFLOPS | Progress: (16/20) | 10.25 s
[Task 7/25] Current/Best: 10.80/ 19.49 GFLOPS | Progress: (20/20) | 12.87 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.65/ 11.41 GFLOPS | Progress: (4/20) | 3.74 s
[Task 8/25] Current/Best: 11.27/ 15.76 GFLOPS | Progress: (8/20) | 7.16 s
[Task 8/25] Current/Best: 11.29/ 15.76 GFLOPS | Progress: (12/20) | 10.54 s
[Task 8/25] Current/Best: 4.45/ 16.31 GFLOPS | Progress: (16/20) | 14.65 s
[Task 8/25] Current/Best: 6.74/ 16.31 GFLOPS | Progress: (20/20) | 16.73 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 7.42/ 16.00 GFLOPS | Progress: (4/20) | 3.27 s
[Task 9/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (8/20) | 5.07 s
[Task 9/25] Current/Best: 20.10/ 20.10 GFLOPS | Progress: (12/20) | 15.93 s
[Task 9/25] Current/Best: 6.46/ 20.10 GFLOPS | Progress: (16/20) | 20.70 s
[Task 9/25] Current/Best: 12.56/ 20.10 GFLOPS | Progress: (20/20) | 24.51 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.49/ 18.49 GFLOPS | Progress: (4/20) | 3.14 s
[Task 10/25] Current/Best: 2.35/ 18.49 GFLOPS | Progress: (8/20) | 5.15 s
[Task 10/25] Current/Best: 9.25/ 18.49 GFLOPS | Progress: (12/20) | 6.93 s
[Task 10/25] Current/Best: 11.72/ 18.49 GFLOPS | Progress: (16/20) | 10.12 s
[Task 10/25] Current/Best: 3.63/ 18.49 GFLOPS | Progress: (20/20)
| 12.15 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 18.20/ 21.03 GFLOPS | Progress: (4/20) | 4.02 s
[Task 11/25] Current/Best: 11.16/ 21.03 GFLOPS | Progress: (8/20) | 7.03 s
[Task 11/25] Current/Best: 7.58/ 21.03 GFLOPS | Progress: (12/20) | 8.99 s
[Task 11/25] Current/Best: 11.93/ 21.03 GFLOPS | Progress: (16/20) | 12.79 s
[Task 11/25] Current/Best: 11.45/ 21.03 GFLOPS | Progress: (20/20) | 15.36 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.82/ 15.82 GFLOPS | Progress: (4/20) | 4.28 s
[Task 12/25] Current/Best: 13.54/ 15.82 GFLOPS | Progress: (8/20) | 9.01 s
[Task 12/25] Current/Best: 11.97/ 16.77 GFLOPS | Progress: (12/20) | 12.08 s
[Task 12/25] Current/Best: 18.71/ 18.71 GFLOPS | Progress: (16/20) | 18.19 s
[Task 12/25] Current/Best: 10.47/ 18.71 GFLOPS | Progress: (20/20) | 23.85 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.75/ 20.41 GFLOPS | Progress: (4/20) | 4.72 s
[Task 13/25] Current/Best: 6.13/ 20.41 GFLOPS | Progress: (8/20) | 6.78 s
[Task 13/25] Current/Best: 12.79/ 20.41 GFLOPS | Progress: (12/20) | 11.31 s
[Task 13/25] Current/Best: 9.98/ 20.41 GFLOPS | Progress: (16/20) | 13.91 s
[Task 13/25] Current/Best: 16.76/ 20.41 GFLOPS | Progress: (20/20) | 17.22 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 18.69/ 18.69 GFLOPS | Progress: (4/20) | 3.27 s
[Task 14/25] Current/Best: 10.50/ 18.69 GFLOPS | Progress: (8/20) | 4.94 s
[Task 14/25] Current/Best: 19.61/ 19.61 GFLOPS | Progress: (12/20) | 6.60 s
[Task 14/25] Current/Best: 2.59/ 19.61 GFLOPS | Progress: (16/20) | 9.52 s
[Task 14/25] Current/Best: 11.05/ 19.61 GFLOPS | Progress: (20/20) | 12.09 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 18.57/ 18.57 GFLOPS | Progress: (4/20) | 7.60 s
[Task 1/25] Current/Best: 16.91/ 18.57 GFLOPS | Progress: (8/20) | 10.42 s
[Task 1/25] Current/Best: 16.80/ 18.57 GFLOPS | Progress: (12/20) | 13.66 s
[Task 1/25] Current/Best: 14.98/ 18.57 GFLOPS | Progress: (16/20) | 15.77 s
[Task 1/25] Current/Best: 12.23/ 19.15 GFLOPS | Progress: (20/20) | 18.24 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 22.16/ 22.16 GFLOPS | Progress: (4/20) | 3.06 s
[Task 2/25] Current/Best: 6.83/ 22.16 GFLOPS | Progress: (8/20) | 4.35 s
[Task 2/25] Current/Best: 20.25/ 22.16 GFLOPS | Progress: (12/20) | 5.39 s
[Task 2/25] Current/Best: 16.71/ 22.16 GFLOPS | Progress: (16/20) | 6.87 s
[Task 2/25] Current/Best: 17.65/ 22.16 GFLOPS | Progress: (20/20) | 8.05 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 22.36 GFLOPS | Progress: (4/20) | 4.95 s
[Task 3/25] Current/Best: 12.65/ 22.36 GFLOPS | Progress: (8/20) | 6.80 s
[Task 3/25] Current/Best: 19.14/ 22.36 GFLOPS | Progress: (12/20) | 8.51 s
[Task 3/25] Current/Best: 12.33/ 22.36 GFLOPS | Progress: (16/20) | 10.54 s
[Task 3/25] Current/Best: 6.68/ 22.36 GFLOPS | Progress: (20/20) | 12.81 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 17.71/ 21.62 GFLOPS | Progress: (4/20) | 4.30 s
[Task 4/25] Current/Best: 9.17/ 21.62 GFLOPS | Progress: (8/20) | 9.83 s
[Task 4/25] Current/Best: 9.92/ 21.62 GFLOPS | Progress: (12/20) | 14.42 s
[Task 4/25] Current/Best: 12.52/ 21.62 GFLOPS | Progress: (16/20) | 23.35 s
[Task 4/25] Current/Best: 16.18/ 21.62 GFLOPS | Progress: (20/20) | 27.98 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 12.33/ 13.42 GFLOPS | Progress: (4/20) | 3.85 s
[Task 5/25] Current/Best: 9.88/ 16.16 GFLOPS | Progress: (8/20) | 5.46 s
[Task 5/25] Current/Best: 16.40/ 17.62 GFLOPS | Progress: (12/20) | 7.21 s
[Task 5/25] Current/Best: 3.36/ 17.62 GFLOPS | Progress: (16/20) | 9.92 s
[Task 5/25] Current/Best: 5.50/ 20.31 GFLOPS | Progress: (20/20) | 11.59 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.37/ 17.07 GFLOPS | Progress: (4/20) | 3.69 s
[Task 6/25] Current/Best: 3.99/ 17.68 GFLOPS | Progress: (8/20) | 6.38 s
[Task 6/25] Current/Best: 15.64/ 17.68 GFLOPS | Progress: (12/20) | 8.20 s
[Task 6/25] Current/Best: 13.00/ 17.68 GFLOPS | Progress: (16/20) | 10.82 s
[Task 6/25] Current/Best: 7.93/ 17.68 GFLOPS | Progress: (20/20) | 13.97 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.62/ 15.62 GFLOPS | Progress: (4/20) | 3.58 s
[Task 7/25] Current/Best: 14.91/ 15.62 GFLOPS | Progress: (8/20) | 6.46 s
[Task 7/25] Current/Best: 16.61/ 16.61 GFLOPS | Progress: (12/20) | 10.07 s
[Task 7/25] Current/Best: 11.86/ 16.61 GFLOPS | Progress: (16/20) | 12.72 s
[Task 7/25] Current/Best: 6.03/ 16.61 GFLOPS | Progress: (20/20) | 14.95 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.51/ 14.97 GFLOPS | Progress: (4/20) | 4.22 s
[Task 8/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (8/20) | 6.18 s
[Task 8/25] Current/Best: 19.87/ 19.87 GFLOPS | Progress: (12/20) | 10.20 s
[Task 8/25] Current/Best: 2.98/ 20.25 GFLOPS | Progress: (16/20) | 12.51 s
[Task 8/25] Current/Best: 11.80/ 20.25 GFLOPS | Progress: (20/20) | 15.83 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 4.86/ 13.17 GFLOPS | Progress: (4/20) | 9.09 s
[Task 9/25] Current/Best: 9.10/ 20.90 GFLOPS | Progress: (8/20) | 10.62 s
[Task 9/25] Current/Best: 14.78/ 20.90 GFLOPS | Progress: (12/20) | 20.12 s
[Task 9/25] Current/Best: 15.19/ 20.90 GFLOPS | Progress: (16/20) | 30.88 s
[Task 9/25] Current/Best: 13.54/ 20.90 GFLOPS | Progress: (20/20) | 36.21 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.53/ 16.45 GFLOPS | Progress: (4/20) | 2.84 s
[Task 10/25] Current/Best: 2.95/ 16.45 GFLOPS | Progress: (8/20) | 5.17 s
[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (12/20) | 6.55 s
[Task 10/25] Current/Best: 13.77/ 18.86 GFLOPS | Progress: (16/20) | 8.11 s
[Task 10/25] Current/Best: 5.18/ 18.86 GFLOPS | Progress: (20/20)
| 9.99 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 22.64/ 22.64 GFLOPS | Progress: (4/20) | 3.42 s
[Task 11/25] Current/Best: 3.09/ 22.64 GFLOPS | Progress: (8/20) | 6.26 s
[Task 11/25] Current/Best: 13.91/ 22.64 GFLOPS | Progress: (12/20) | 10.30 s
[Task 11/25] Current/Best: 10.93/ 22.64 GFLOPS | Progress: (16/20) | 12.49 s
[Task 11/25] Current/Best: 11.36/ 22.64 GFLOPS | Progress: (20/20) | 14.40 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 12.65/ 13.28 GFLOPS | Progress: (4/20) | 4.74 s
[Task 12/25] Current/Best: 13.34/ 13.34 GFLOPS | Progress: (8/20) | 7.87 s
[Task 12/25] Current/Best: 1.60/ 15.13 GFLOPS | Progress: (12/20) | 11.30 s
[Task 12/25] Current/Best: 15.56/ 15.56 GFLOPS | Progress: (16/20) | 13.12 s
[Task 12/25] Current/Best: 9.97/ 15.56 GFLOPS | Progress: (20/20) | 16.28 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 16.96/ 16.96 GFLOPS | Progress: (4/20) | 4.50 s
[Task 13/25] Current/Best: 9.62/ 18.86 GFLOPS | Progress: (8/20) | 7.32 s
[Task 13/25] Current/Best: 16.48/ 18.86 GFLOPS | Progress: (12/20) | 10.28 s
[Task 13/25] Current/Best: 7.00/ 18.86 GFLOPS | Progress: (16/20) | 13.46 s
[Task 13/25] Current/Best: 8.55/ 18.86 GFLOPS | Progress: (20/20) | 15.61 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.05/ 15.05 GFLOPS | Progress: (4/20) | 3.26 s
[Task 14/25] Current/Best: 6.31/ 15.05 GFLOPS | Progress: (8/20) | 6.81 s
[Task 14/25] Current/Best: 8.37/ 15.05 GFLOPS | Progress: (12/20) | 10.72 s Done.
+
[Task 14/25] Current/Best: 15.68/ 18.87 GFLOPS | Progress: (16/20) | 12.34 s
[Task 14/25] Current/Best: 11.30/ 18.87 GFLOPS | Progress: (20/20) | 16.07 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 10.87/ 20.44 GFLOPS | Progress: (4/20) | 5.86 s
[Task 15/25] Current/Best: 12.18/ 20.44 GFLOPS | Progress: (8/20) | 8.18 s
[Task 15/25] Current/Best: 11.63/ 20.44 GFLOPS | Progress: (12/20) | 10.71 s
[Task 15/25] Current/Best: 3.05/ 20.44 GFLOPS | Progress: (16/20) | 13.27 s
[Task 15/25] Current/Best: 19.41/ 20.44 GFLOPS | Progress: (20/20) | 16.45 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 6.52/ 16.18 GFLOPS | Progress: (4/20) | 2.98 s
[Task 16/25] Current/Best: 11.80/ 18.08 GFLOPS | Progress: (8/20) | 6.26 s
[Task 16/25] Current/Best: 5.81/ 18.08 GFLOPS | Progress: (12/20) | 7.98 s
[Task 16/25] Current/Best: 11.62/ 18.08 GFLOPS | Progress: (16/20) | 10.75 s
[Task 16/25] Current/Best: 6.07/ 18.08 GFLOPS | Progress: (20/20)
| 12.89 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.38/ 12.79 GFLOPS | Progress: (4/20) | 5.96 s
[Task 17/25] Current/Best: 6.42/ 18.81 GFLOPS | Progress: (8/20) | 8.49 s
[Task 17/25] Current/Best: 9.38/ 18.81 GFLOPS | Progress: (12/20) | 10.82 s
[Task 17/25] Current/Best: 11.72/ 18.81 GFLOPS | Progress: (16/20) | 13.18 s
[Task 17/25] Current/Best: 20.88/ 20.88 GFLOPS | Progress: (20/20) | 17.17 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 9.76/ 19.13 GFLOPS | Progress: (4/20) | 4.54 s
[Task 18/25] Current/Best: 15.03/ 19.13 GFLOPS | Progress: (8/20) | 6.19 s
[Task 18/25] Current/Best: 5.11/ 19.13 GFLOPS | Progress: (12/20) | 12.72 s
[Task 18/25] Current/Best: 11.40/ 19.13 GFLOPS | Progress: (16/20) | 17.18 s
[Task 18/25] Current/Best: 10.36/ 19.13 GFLOPS | Progress: (20/20) | 19.93 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 8.69/ 17.13 GFLOPS | Progress: (4/20) | 5.23 s
[Task 19/25] Current/Best: 9.20/ 17.13 GFLOPS | Progress: (8/20) | 9.01 s
[Task 19/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 11.60 s
[Task 19/25] Current/Best: 14.30/ 19.28 GFLOPS | Progress: (16/20) | 13.63 s
[Task 19/25] Current/Best: 17.84/ 19.28 GFLOPS | Progress: (20/20) | 18.57 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.10/ 16.26 GFLOPS | Progress: (4/20) | 3.27 s
[Task 20/25] Current/Best: 8.52/ 16.26 GFLOPS | Progress: (8/20) | 5.74 s
[Task 20/25] Current/Best: 2.24/ 16.26 GFLOPS | Progress: (12/20) | 10.53 s Done.
+
[Task 20/25] Current/Best: 15.79/ 21.25 GFLOPS | Progress: (16/20) | 12.63 s
[Task 20/25] Current/Best: 16.87/ 21.25 GFLOPS | Progress: (20/20) | 14.17 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 5.31/ 15.36 GFLOPS | Progress: (4/20) | 5.43 s
[Task 21/25] Current/Best: 12.15/ 15.36 GFLOPS | Progress: (8/20) | 6.79 s
[Task 21/25] Current/Best: 14.87/ 15.36 GFLOPS | Progress: (12/20) | 9.15 s
[Task 21/25] Current/Best: 22.00/ 22.00 GFLOPS | Progress: (16/20) | 12.14 s
[Task 21/25] Current/Best: 2.28/ 22.00 GFLOPS | Progress: (20/20) | 13.78 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 8.02/ 17.58 GFLOPS | Progress: (4/20) | 3.78 s
[Task 22/25] Current/Best: 15.40/ 18.20 GFLOPS | Progress: (8/20) | 5.08 s
[Task 22/25] Current/Best: 9.61/ 18.69 GFLOPS | Progress: (12/20)
| 6.60 s
[Task 22/25] Current/Best: 16.90/ 18.69 GFLOPS | Progress: (16/20) | 7.86 s
[Task 22/25] Current/Best: 9.08/ 20.96 GFLOPS | Progress: (20/20) | 10.58 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 11.08/ 20.83 GFLOPS | Progress: (4/20) | 3.83 s
[Task 23/25] Current/Best: 3.08/ 22.60 GFLOPS | Progress: (8/20) | 6.64 s
[Task 23/25] Current/Best: 19.49/ 22.60 GFLOPS | Progress: (12/20) | 9.41 s
[Task 23/25] Current/Best: 16.18/ 23.01 GFLOPS | Progress: (16/20) | 12.59 s
[Task 23/25] Current/Best: 9.15/ 23.01 GFLOPS | Progress: (20/20) | 15.55 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.55/ 5.74 GFLOPS | Progress: (4/20) | 9.53 s
[Task 24/25] Current/Best: 3.64/ 9.34 GFLOPS | Progress: (8/20) | 20.22 s
[Task 24/25] Current/Best: 6.02/ 9.34 GFLOPS | Progress: (12/20) | 30.98 s Done.
Done.
-
[Task 15/25] Current/Best: 15.86/ 17.85 GFLOPS | Progress: (4/20) | 3.24 s
[Task 15/25] Current/Best: 15.89/ 17.85 GFLOPS | Progress: (8/20) | 5.39 s
[Task 15/25] Current/Best: 12.20/ 17.85 GFLOPS | Progress: (12/20) | 8.62 s
[Task 15/25] Current/Best: 15.99/ 18.75 GFLOPS | Progress: (16/20) | 11.35 s
[Task 15/25] Current/Best: 7.30/ 18.75 GFLOPS | Progress: (20/20) | 15.38 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 7.53/ 16.15 GFLOPS | Progress: (4/20) | 4.84 s
[Task 16/25] Current/Best: 10.20/ 18.65 GFLOPS | Progress: (8/20) | 7.44 s
[Task 16/25] Current/Best: 17.96/ 18.65 GFLOPS | Progress: (12/20) | 9.59 s
[Task 16/25] Current/Best: 16.65/ 18.65 GFLOPS | Progress: (16/20) | 12.57 s
[Task 16/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (20/20) | 16.15 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 17.59/ 21.82 GFLOPS | Progress: (4/20) | 3.75 s
[Task 17/25] Current/Best: 3.09/ 21.82 GFLOPS | Progress: (8/20) | 6.87 s
[Task 17/25] Current/Best: 6.18/ 21.82 GFLOPS | Progress: (12/20) | 9.21 s
[Task 17/25] Current/Best: 19.24/ 21.82 GFLOPS | Progress: (16/20) | 10.95 s
[Task 17/25] Current/Best: 11.49/ 21.82 GFLOPS | Progress: (20/20) | 14.37 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 15.04/ 20.12 GFLOPS | Progress: (4/20) | 4.56 s
[Task 18/25] Current/Best: 6.10/ 20.12 GFLOPS | Progress: (8/20) | 11.42 s
[Task 18/25] Current/Best: 12.42/ 20.12 GFLOPS | Progress: (12/20) | 15.42 s
[Task 18/25] Current/Best: 14.34/ 20.12 GFLOPS | Progress: (16/20) | 19.35 s
[Task 18/25] Current/Best: 14.11/ 20.12 GFLOPS | Progress: (20/20) | 21.51 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 14.51/ 17.87 GFLOPS | Progress: (4/20) | 4.17 s
[Task 19/25] Current/Best: 11.62/ 17.87 GFLOPS | Progress: (8/20) | 7.06 s
[Task 19/25] Current/Best: 12.35/ 17.87 GFLOPS | Progress: (12/20) | 10.69 s
[Task 19/25] Current/Best: 10.59/ 17.87 GFLOPS | Progress: (16/20) | 14.23 s
[Task 19/25] Current/Best: 7.86/ 17.87 GFLOPS | Progress: (20/20) | 22.23 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 14.47/ 14.47 GFLOPS | Progress: (4/20) | 4.45 s
[Task 20/25] Current/Best: 17.07/ 17.07 GFLOPS | Progress: (8/20) | 6.93 s
[Task 20/25] Current/Best: 15.12/ 17.07 GFLOPS | Progress: (12/20) | 9.74 s
[Task 20/25] Current/Best: 12.04/ 17.07 GFLOPS | Progress: (16/20) | 12.26 s
[Task 20/25] Current/Best: 17.84/ 17.84 GFLOPS | Progress: (20/20) | 13.68 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 14.21/ 17.23 GFLOPS | Progress: (4/20) | 3.81 s
[Task 21/25] Current/Best: 8.85/ 17.75 GFLOPS | Progress: (8/20) | 5.84 s
[Task 21/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (12/20) | 7.23 s
[Task 21/25] Current/Best: 12.91/ 18.44 GFLOPS | Progress: (16/20) | 9.81 s
[Task 21/25] Current/Best: 1.60/ 18.44 GFLOPS | Progress: (20/20) |
11.81 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 17.46/ 18.05 GFLOPS | Progress: (4/20) | 3.65 s
[Task 22/25] Current/Best: 19.70/ 19.70 GFLOPS | Progress: (8/20) | 5.46 s Done.
- Done.
-
[Task 22/25] Current/Best: 7.06/ 19.70 GFLOPS | Progress: (12/20) | 8.64 s
[Task 22/25] Current/Best: 14.82/ 19.70 GFLOPS | Progress: (16/20) | 10.08 s
[Task 22/25] Current/Best: 13.20/ 19.95 GFLOPS | Progress: (20/20) | 11.84 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.13/ 20.99 GFLOPS | Progress: (4/20) | 3.70 s
[Task 23/25] Current/Best: 9.37/ 20.99 GFLOPS | Progress: (8/20) | 6.90 s
[Task 23/25] Current/Best: 13.51/ 20.99 GFLOPS | Progress: (12/20) | 9.41 s
[Task 23/25] Current/Best: 1.55/ 22.39 GFLOPS | Progress: (16/20) | 13.33 s
[Task 23/25] Current/Best: 8.71/ 22.39 GFLOPS | Progress: (20/20) | 18.88 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.16/ 7.16 GFLOPS | Progress: (4/20) | 12.06 s
[Task 24/25] Current/Best: 9.83/ 9.83 GFLOPS | Progress: (8/20) | 23.43 s
[Task 24/25] Current/Best: 0.00/ 9.83 GFLOPS | Progress: (12/20) | 34.70 s
[Task 24/25] Current/Best: 7.04/ 9.83 GFLOPS | Progress: (16/20) | 37.90 s
[Task 24/25] Current/Best: 2.98/ 9.83 GFLOPS | Progress: (20/20) | 41.10 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 2.83/ 8.77 GFLOPS | Progress: (4/20) | 10.15 s
[Task 25/25] Current/Best: 1.53/ 8.92 GFLOPS | Progress: (8/20) | 20.86 s
[Task 25/25] Current/Best: 8.78/ 8.92 GFLOPS | Progress: (12/20) | 24.74 s
[Task 25/25] Current/Best: 7.92/ 8.92 GFLOPS | Progress: (16/20) | 26.33 s
[Task 25/25] Current/Best: 2.54/ 8.92 GFLOPS | Progress: (20/20) | 30.31 s
+
[Task 24/25] Current/Best: 7.73/ 9.34 GFLOPS | Progress: (16/20) | 41.72 s
[Task 24/25] Current/Best: 5.62/ 9.34 GFLOPS | Progress: (20/20) | 51.99 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 3.40/ 8.98 GFLOPS | Progress: (4/20) | 11.17 s
[Task 25/25] Current/Best: 7.56/ 8.98 GFLOPS | Progress: (8/20) | 16.40 s
[Task 25/25] Current/Best: 8.64/ 8.98 GFLOPS | Progress: (12/20) | 27.13 s
[Task 25/25] Current/Best: 8.34/ 8.98 GFLOPS | Progress: (16/20) | 28.97 s
[Task 25/25] Current/Best: 8.36/ 8.98 GFLOPS | Progress: (20/20) | 31.17 s
@@ -673,8 +673,8 @@ 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='n02123045 tabby, tabby cat' with probability=0.621105
+ class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -731,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 442.9666855599862, 'median': 442.5070033999873, 'std': 3.578336566890116}
- unoptimized: {'mean': 519.4300110699987, 'median': 519.3191480999758, 'std': 2.1550682887027333}
+ optimized: {'mean': 431.94241448000184, 'median': 430.1035603500054, 'std': 3.690289162052112}
+ unoptimized: {'mean': 522.3170279700014, 'median': 521.8688147500018, 'std': 2.37780837536643}
@@ -755,7 +755,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 52.379 seconds)
+ **Total running time of the script:** ( 11 minutes 8.410 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 a06f1f300a..5b61b69ebe 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.278e-07 secs/op
+ 1.327e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 73f9947a15..ac6c1fe783 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xc06ef10)), stage(b, placeholder(b, 0x202a8ea0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x6278890)), stage(b, placeholder(b, 0x4ab4a00)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index d304d1f0d1..30eb71ec9e 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:21.722** total execution time for **tutorial** files:
+**14:17.235** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:52.379 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:08.410 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:35.173 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:10.817 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.020 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.065 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.818 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.021 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:14.836 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.008 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.765 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.966 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.543 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.764 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.177 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.174 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 6db50cf9a6..1e9112fe29 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -295,7 +295,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000007
- naive: 0.000007
+ naive: 0.000009
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000010
@@ -449,7 +449,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000024
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.113560004654574e-06 1.0
- naive 6.6567e-06 0.9357761789658569
- parallel 7.105599999999999e-06 0.998881009698468
- vector 2.46347e-05 3.4630620932249006
+ numpy 7.171100000959996e-06 1.0
+ naive 8.849700000000001e-06 1.2340784536284937
+ parallel 9.559399999999999e-06 1.3330451393398894
+ vector 2.4474000000000003e-05 3.4128655292387036
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018855
+ Numpy running time: 0.018800
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.366492
+ none: 3.458474
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.326488
+ blocking: 0.320841
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.355809
+ vectorization: 0.348954
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.119804
+ loop permutation: 0.120047
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108172
+ array packing: 0.108854
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111509
+ block caching: 0.110444
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.147377
+ parallelization: 0.146763
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.366491934 1.0
- blocking 0.326487601 0.0969815485677026
- vectorization 0.355808592 0.1056912058533392
- loop permutation 0.1198037614 0.03558712266322038
- array packing 0.1081721407 0.03213200649837054
- block caching 0.1115092723 0.033123285154438756
- parallelization 0.1473768667 0.04377757903162111
+ none 3.4584738125000003 1.0
+ blocking 0.32084117419999997 0.09276958323072453
+ vectorization 0.3489542188 0.1008983261746181
+ loop permutation 0.12004747190000001 0.0347111120130825
+ array packing 0.1088536999 0.031474490136825344
+ block caching 0.1104443762 0.03193442604677811
+ parallelization 0.1467633573 0.042435873525932616
@@ -1663,7 +1663,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.020 seconds)
+ **Total running time of the script:** ( 1 minutes 2.065 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 5ee560cd36..26774f39be 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-d261fa883811209144cb3525982086cba8a2c831
+ff6aaeb12ae71393fef37da8f9c72a0f2017e6d5
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 90510501a3..1c49f33462 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 16.278 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.441 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 3966c6b2fc..31ab64d800 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 989ms/step
+1/1 [==============================] - 1s 980ms/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 b59f7598e3..7749d39915 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6457ea1a-270a-4183-a2db-3d250161f548 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.zip2aa13670-20ae-46b7-b08c-b23125a3ed99 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 4ead6dfce6..3ea892c4d9 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,14 +448,13 @@ 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<00:00, 54.7MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 40.4MB/s]
- 44%|####4 | 18.3M/41.5M [00:00<00:00, 37.8MB/s]
- 57%|#####6 | 23.6M/41.5M [00:00<00:00, 42.8MB/s]
- 67%|######7 | 27.8M/41.5M [00:00<00:00, 36.8MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 32.8MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 32.1MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 35.8MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 60.5MB/s]
+ 29%|##9 | 12.2M/41.5M [00:00<00:00, 61.1MB/s]
+ 43%|####3 | 18.0M/41.5M [00:00<00:00, 43.4MB/s]
+ 54%|#####4 | 22.6M/41.5M [00:00<00:00, 38.9MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.9MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 46.1MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 47.4MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index f6d546ecd6..acbd37f3be 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,13 +431,12 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 58.0MB/s]
- 33%|###3 | 14.8M/44.7M [00:00<00:00, 64.3MB/s]
- 48%|####8 | 21.6M/44.7M [00:00<00:00, 67.7MB/s]
- 63%|######3 | 28.2M/44.7M [00:00<00:00, 60.0MB/s]
- 76%|#######6 | 34.1M/44.7M [00:00<00:00, 46.4MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 46.9MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 56.6MB/s]
+ 14%|#4 | 6.30M/44.7M [00:00<00:00, 46.9MB/s]
+ 24%|##4 | 10.8M/44.7M [00:00<00:00, 42.5MB/s]
+ 44%|####3 | 19.5M/44.7M [00:00<00:00, 61.7MB/s]
+ 58%|#####8 | 26.1M/44.7M [00:00<00:00, 57.3MB/s]
+ 83%|########2 | 37.1M/44.7M [00:00<00:00, 75.6MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 68.0MB/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 a3c6eb9e7e..b55553ca50 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.360 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.819 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 08920ac754..31ec03519c 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:59.714</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:55.086</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_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>01:16.278</p></td>
+<td><p>01:14.441</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>01:13.360</p></td>
+<td><p>01:12.819</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:48.676</p></td>
+<td><p>00:47.183</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:33.361</p></td>
+<td><p>00:32.839</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.770</p></td>
+<td><p>00:30.491</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:27.210</p></td>
+<td><p>00:27.411</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>00:26.279</p></td>
+<td><p>00:25.782</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>00:24.061</p></td>
+<td><p>00:23.212</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>00:18.265</p></td>
+<td><p>00:18.497</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>00:02.454</p></td>
+<td><p>00:02.410</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index eddb0e3d94..087eff6803 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)
- 17.2892 16.6748 22.6245 16.2313 1.8203
+ 16.2720 16.1847 17.1205 16.1231 0.2844
</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 d050bee392..dda2702458 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,32 +453,21 @@ 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]
- 4%|3 | 6.30M/170M [00:00<00:04, 36.0MB/s]
- 6%|5 | 9.74M/170M [00:00<00:05, 32.3MB/s]
- 9%|9 | 16.0M/170M [00:00<00:04, 35.1MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:03, 44.7MB/s]
- 18%|#7 | 30.3M/170M [00:00<00:03, 48.3MB/s]
- 21%|## | 35.0M/170M [00:00<00:03, 43.9MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:03, 43.7MB/s]
- 28%|##8 | 48.0M/170M [00:01<00:02, 46.7MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 48.4MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:02, 47.8MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 53.8MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 56.9MB/s]
- 51%|##### | 86.3M/170M [00:01<00:01, 49.9MB/s]
- 54%|#####3 | 91.2M/170M [00:02<00:01, 49.6MB/s]
- 57%|#####6 | 96.1M/170M [00:02<00:01, 42.4MB/s]
- 60%|###### | 102M/170M [00:02<00:01, 46.1MB/s]
- 63%|######2 | 107M/170M [00:02<00:01, 40.7MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 43.1MB/s]
- 71%|####### | 120M/170M [00:02<00:01, 42.9MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 47.3MB/s]
- 80%|######## | 136M/170M [00:03<00:00, 50.0MB/s]
- 85%|########4 | 144M/170M [00:03<00:00, 46.9MB/s]
- 89%|########9 | 152M/170M [00:03<00:00, 49.3MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 47.6MB/s]
- 99%|#########8| 168M/170M [00:03<00:00, 54.3MB/s]
-100%|##########| 170M/170M [00:03<00:00, 47.6MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:01, 148MB/s]
+ 17%|#6 | 28.4M/170M [00:00<00:01, 118MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:01, 117MB/s]
+ 30%|### | 51.3M/170M [00:00<00:01, 112MB/s]
+ 37%|###6 | 62.3M/170M [00:00<00:01, 104MB/s]
+ 43%|####2 | 72.4M/170M [00:00<00:01, 98.7MB/s]
+ 52%|#####1 | 88.0M/170M [00:00<00:00, 105MB/s]
+ 58%|#####7 | 98.0M/170M [00:00<00:00, 102MB/s]
+ 63%|######3 | 108M/170M [00:01<00:00, 96.7MB/s]
+ 71%|####### | 120M/170M [00:01<00:00, 101MB/s]
+ 76%|#######6 | 130M/170M [00:01<00:00, 94.8MB/s]
+ 85%|########4 | 144M/170M [00:01<00:00, 107MB/s]
+ 91%|######### | 154M/170M [00:01<00:00, 88.9MB/s]
+ 96%|#########6| 163M/170M [00:01<00:00, 82.9MB/s]
+100%|##########| 170M/170M [00:01<00:00, 99.3MB/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=& [...]
@@ -576,7 +565,7 @@ 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 25.440 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.583 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 401f99cd87..39ab3ec0d4 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 48.6MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 57.2MB/s]
+ 86%|########5 | 11.7M/13.6M [00:00<00:00, 122MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 118MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.5040 90.4217 91.2382 90.1251 0.2516
+ 90.3706 90.3013 93.3681 90.1156 0.3427
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.737 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.477 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 bbb1256a05..7f28ef0863 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.4490 120.3405 122.6966 119.2738 0.5330
+ 120.0229 120.0081 124.9250 119.2927 0.5624
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.799 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 29.539 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 f0bb5dc8fd..088f1bd4bc 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.468 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.425 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 ba35ee5311..37955843f5 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,23 +462,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|3 | 5262/132723 [00:00<00:02, 52609.26KB/s]
- 10%|# | 13726/132723 [00:00<00:01, 71434.50KB/s]
- 16%|#5 | 20870/132723 [00:00<00:01, 59857.38KB/s]
- 22%|##2 | 29345/132723 [00:00<00:01, 68650.48KB/s]
- 27%|##7 | 36427/132723 [00:00<00:01, 50649.96KB/s]
- 34%|###3 | 44834/132723 [00:00<00:01, 59310.02KB/s]
- 40%|#### | 53244/132723 [00:00<00:01, 66006.32KB/s]
- 47%|####6 | 61733/132723 [00:00<00:00, 71263.51KB/s]
- 53%|#####2 | 70255/132723 [00:01<00:00, 75233.62KB/s]
- 59%|#####9 | 78768/132723 [00:01<00:00, 78091.66KB/s]
- 66%|######5 | 87212/132723 [00:01<00:00, 79945.12KB/s]
- 72%|#######2 | 95708/132723 [00:01<00:00, 81418.72KB/s]
- 79%|#######8 | 104230/132723 [00:01<00:00, 82541.94KB/s]
- 85%|########4 | 112702/132723 [00:01<00:00, 83187.75KB/s]
- 91%|#########1| 121096/132723 [00:01<00:00, 55201.00KB/s]
- 98%|#########7| 129624/132723 [00:01<00:00, 61813.24KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 67544.26KB/s]
+ 5%|4 | 6453/132723 [00:00<00:01, 64521.45KB/s]
+ 11%|# | 14409/132723 [00:00<00:01, 73361.45KB/s]
+ 16%|#6 | 21746/132723 [00:00<00:02, 50473.22KB/s]
+ 22%|##2 | 29674/132723 [00:00<00:01, 59390.71KB/s]
+ 28%|##8 | 37622/132723 [00:00<00:01, 65551.19KB/s]
+ 34%|###4 | 45513/132723 [00:00<00:01, 69615.75KB/s]
+ 40%|#### | 53538/132723 [00:00<00:01, 72837.53KB/s]
+ 46%|####6 | 61543/132723 [00:00<00:00, 75013.88KB/s]
+ 52%|#####2 | 69597/132723 [00:00<00:00, 76677.68KB/s]
+ 58%|#####8 | 77491/132723 [00:01<00:00, 77356.24KB/s]
+ 64%|######4 | 85520/132723 [00:01<00:00, 78237.31KB/s]
+ 70%|####### | 93521/132723 [00:01<00:00, 78766.17KB/s]
+ 77%|#######6 | 101551/132723 [00:01<00:00, 79224.56KB/s]
+ 83%|########2 | 109510/132723 [00:01<00:00, 78349.56KB/s]
+ 88%|########8 | 117447/132723 [00:01<00:00, 78649.70KB/s]
+ 95%|#########4| 125449/132723 [00:01<00:00, 79056.65KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 73940.69KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +517,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 7.496 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 3.561 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 5f504a0b16..c72968b66e 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>13:22.086</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:11.600</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:25.440</p></td>
+<td><p>03:20.583</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:07.496</p></td>
+<td><p>03:03.561</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>02:28.799</p></td>
+<td><p>02:29.539</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>01:42.468</p></td>
+<td><p>01:41.425</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>01:07.737</p></td>
+<td><p>01:07.477</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:37.605</p></td>
+<td><p>00:36.987</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:26.722</p></td>
+<td><p>00:26.359</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:25.812</p></td>
+<td><p>00:25.661</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 4016ffc87f..869643e936 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipd8ea5ee0-8ad0-45bb-aa4c-ccdd5fd695f7 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.zip8399a51e-0b6d-4b1e-90f9-41682026ce8e 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 43b58894d9..278d337963 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>00:48.636</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:47.916</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>00:45.058</p></td>
+<td><p>00:44.351</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>00:02.498</p></td>
+<td><p>00:02.479</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.072</p></td>
+<td><p>00:01.079</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 624de3dd8a..35801f0336 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6997us [6997us] (45.83%; 45.83%)
-FoldScaleAxis: 8269us [8us] (54.17%; 54.17%)
- FoldConstant: 8261us [1609us] (54.12%; 99.90%)
- InferType: 6653us [6653us] (43.58%; 80.53%)
+InferType: 6838us [6838us] (46.19%; 46.19%)
+FoldScaleAxis: 7967us [6us] (53.81%; 53.81%)
+ FoldConstant: 7962us [1631us] (53.77%; 99.93%)
+ InferType: 6331us [6331us] (42.76%; 79.52%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6795us [6795us] (40.12%; 40.12%)
-FoldScaleAxis: 10140us [8us] (59.88%; 59.88%)
- FoldConstant: 10133us [1682us] (59.83%; 99.92%)
- InferType: 8451us [8451us] (49.90%; 83.40%)
+InferType: 6567us [6567us] (45.17%; 45.17%)
+FoldScaleAxis: 7970us [6us] (54.83%; 54.83%)
+ FoldConstant: 7964us [1671us] (54.79%; 99.93%)
+ InferType: 6294us [6294us] (43.30%; 79.02%)
</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 4271c0a5f1..508810855e 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.237728 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 36.486686 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 26bd19a520..f24a8462aa 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -916,7 +916,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.378775 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.350697 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 faf01e4798..1ded5e9a8b 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019544
-Baseline: 3.365354
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019089
+Baseline: 3.422495
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -535,7 +535,7 @@ 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: 0.331463
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.326122
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -602,7 +602,7 @@ 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: 0.348065
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.349573
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -663,7 +663,7 @@ 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: 0.126888
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.122556
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -746,7 +746,7 @@ 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: 0.110085
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110757
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -832,7 +832,7 @@ 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: 0.111257
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111784
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -922,7 +922,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148202
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148735
</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 c0ecab702f..31f527b44d 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.551</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.749</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>00:33.006</p></td>
+<td><p>00:33.080</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>00:01.455</p></td>
+<td><p>00:01.538</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>00:01.091</p></td>
+<td><p>00:01.130</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 f72cf905ab..c41653d638 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>08:55.132</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:57.778</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>05:23.556</p></td>
+<td><p>05:24.912</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>01:34.746</p></td>
+<td><p>01:34.824</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>01:04.744</p></td>
+<td><p>01:04.081</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:28.092</p></td>
+<td><p>00:30.298</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.446</p></td>
+<td><p>00:12.220</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.549</p></td>
+<td><p>00:11.442</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 7d5905dc96..dfb1f80dc7 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
@@ -504,482 +504,781 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
- }
+ let cse_var_1: int32 = (rc.outer.outer*392)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 14)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 14), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 28)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 28), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 42)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 6), 9)) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 42), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 70)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 70), 81)) && (floormod((threadIdx.x_1 + 70), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 70), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 84)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 84), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 126)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 126), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 5)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 140)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 140), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 154)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 73), 81)) && (floormod((threadIdx.x_1 + 73), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 154), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 73), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 182)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 182), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 210)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 210), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((threadIdx.x_1 < 10) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 238)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 238), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 252)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 252), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 1)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 266)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 266), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 6), 9)) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 308)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 308), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 322)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 322), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 350)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 350), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 26), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 364)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 364), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 40), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 378)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 378), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 6)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 406)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 1), 81)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 406), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 420)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 6), 9)) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 420), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 15), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 434)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 434), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 462)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 462), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 57), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 476)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 71), 81)) && (floormod((threadIdx.x_1 + 71), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 476), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 71), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 518)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 518), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 532)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 532), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 546)] = @tir.if_then_else((((threadIdx.x_1 < 12) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 546), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 574)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 7), 81)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 574), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 7), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 602)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 602), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ pad_temp.shared_1[(threadIdx.x_1 + 630)] = @tir.if_then_else((((threadIdx.x_1 < 9) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 630), 81)*49)) + threadIdx.x_1) + 41)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14;
+ if @tir.likely((threadIdx.x_1 < 4), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 644)] = 0f32
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 14 {
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope="shared")[(threadIdx.x_2*48)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*16), 24), 3)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 1)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*16), 24), 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 2)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*16), 24), 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 3)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 4)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 5)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 6)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 7)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 8)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 9)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 10)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 11)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 12)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 13)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 14)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 15)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 16)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 17)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 18)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 19)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 20)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 21)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 22)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 23)] = kernel[((((((blockIdx.x*18432) + (floordiv((threadIdx.x_2*2), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 24)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 25)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 26)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 27)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 28)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 29)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 30)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 31)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 32)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 33)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 34)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 35)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 36)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 37)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 38)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 39)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 40)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 41)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 24), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 42)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 43)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 44)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 24), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 45)] = kernel[(((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 46)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 6), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*48) + 47)] = kernel[((((((blockIdx.x*18432) + (floordiv(((threadIdx.x_2*2) + 1), 3)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*196) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*4) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1017,7 +1316,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.363 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.287 ms
</pre></div>
</div>
</div>
@@ -1046,36 +1345,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
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_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
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_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1093,14 +1392,14 @@ 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=48)
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=64)
+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=14)
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=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+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=14)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1120,429 +1419,730 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(14) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[288];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 14)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 14) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 28)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 28) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 42)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 42) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 70)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 70) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 84)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 84) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 126)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 126) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 27)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 140)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 140) / 81) * 49)) + (((((int)threadIdx.x) + 59) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 154)] = (((((9 <= ((((int)threadIdx.x) + 73) % 81)) && (((((int)threadIdx.x) + 73) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 154) / 81) * 49)) + ((((((int)threadIdx.x) + 73) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 182)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 182) / 81) * 49)) + (((((int)threadIdx.x) + 20) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 196) / 81) * 49)) + (((((int)threadIdx.x) + 34) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 210)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 210) / 81) * 49)) + (((((int)threadIdx.x) + 48) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((int)threadIdx.x) < 10) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + (((((int)threadIdx.x) + 62) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 238)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 238) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 252)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 252) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 266)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 266) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 294) / 81) * 49)) + (((((int)threadIdx.x) + 51) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 308)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 308) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 322)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 322) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 350)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 350) / 81) * 49)) + (((((int)threadIdx.x) + 26) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 364)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 364) / 81) * 49)) + (((((int)threadIdx.x) + 40) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 378)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 378) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 34)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 406)] = ((((8 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 406) / 81) * 49)) + (((((int)threadIdx.x) + 1) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 420)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 420) / 81) * 49)) + (((((int)threadIdx.x) + 15) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 434)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 434) / 81) * 49)) + (((((int)threadIdx.x) + 29) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + (((((int)threadIdx.x) + 43) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 462)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 462) / 81) * 49)) + (((((int)threadIdx.x) + 57) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 476)] = (((((9 <= ((((int)threadIdx.x) + 71) % 81)) && (((((int)threadIdx.x) + 71) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 476) / 81) * 49)) + ((((((int)threadIdx.x) + 71) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 518)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 518) / 81) * 49)) + (((((int)threadIdx.x) + 32) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 532)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 532) / 81) * 49)) + (((((int)threadIdx.x) + 46) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 546)] = ((((((int)threadIdx.x) < 12) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 546) / 81) * 49)) + (((((int)threadIdx.x) + 60) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 574)] = ((((2 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 574) / 81) * 49)) + (((((int)threadIdx.x) + 7) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 602)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 602) / 81) * 49)) + (((((int)threadIdx.x) + 35) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + (((((int)threadIdx.x) + 49) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 630)] = ((((((int)threadIdx.x) < 9) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 630) / 81) * 49)) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 4) {
+ pad_temp_shared[(((int)threadIdx.x) + 644)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[(((int)threadIdx.x) * 48)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 16) % 24) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 1)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 16) % 24) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 2)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 16) % 24) / 3) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 3)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 1) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 4)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 1) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 5)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 1) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 6)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 2) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 7)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 2) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 8)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 2) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 9)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 10)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 11)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 12)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 4) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 13)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 4) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 14)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 4) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 15)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 5) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 16)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 5) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 17)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 5) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 18)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 2) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 19)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 2) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 20)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 2) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 21)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 7) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 22)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 7) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 23)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) * 2) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 7) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 24)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 8) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 25)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 8) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 26)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 8) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 27)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 3) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 28)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 3) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 29)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 3) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 30)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 10) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 31)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 10) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 32)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 10) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 33)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 11) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 34)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 11) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 35)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 11) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 36)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 4) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 37)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 4) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 38)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 4) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 39)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 13) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 40)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 13) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 41)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 13) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 42)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 14) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 43)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 14) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 44)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) + 14) % 24) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 45)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 5) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 46)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 5) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ }
+ if (((int)threadIdx.x) < 6) {
+ kernel_shared[((((int)threadIdx.x) * 48) + 47)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 16) / 3) + 5) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 4) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1580,7 +2180,7 @@ 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 23.556 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.912 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 8464c4501c..4ac2d1d77c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1967 8.2001 8.2046 8.1852 0.0083
+ 8.2192 8.2236 8.2315 8.2025 0.0122
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.744 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.081 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 13e6122949..a55bde4692 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 775.0565 775.0243 775.8859 774.2594 0.6644
+ 770.8568 771.4724 773.2872 767.8109 2.2777
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.746 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.824 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 9e8366b5b0..b7f11a88f9 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,78 +632,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 1024) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [128], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2)
+ let cse_var_2: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 64)*2048) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_5: int32 = floormod(i0.outer.i1.outer.fused, 64)
+ let cse_var_6: int32 = (cse_var_5*8)
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 64)*4096) + (i0.inner*512)) + cse_var_6)
+ compute[ramp(cse_var_4, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_6) - (floordiv(cse_var_5, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_4, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -741,7 +693,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.717 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.538 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 9f40f6bd87..3b815d31d7 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>00:28.691</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.365</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</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>00:28.655</p></td>
+<td><p>00:46.329</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>
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 bb9805f364..8b85e8180c 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,8 +689,11 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10018948
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1347833
+No: 2 GFLOPS: 27.77/27.77 result: MeasureResult(costs=(0.008337656,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.136690855026245, timestamp=1667434045.462885) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2325325
+No: 3 GFLOPS: 259.24/259.24 result: MeasureResult(costs=(0.000893015107142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.93196702003479, timestamp=1667434047.2434297) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3558974
+No: 4 GFLOPS: 11.30/259.24 result: MeasureResult(costs=(0.020484367333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.858165502548218, timestamp=1667434048.9672313) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3544529
+No: 5 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -812,9 +815,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2864213
-No: 3 GFLOPS: 10.07/10.07 result: MeasureResult(costs=(0.02298654933333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.742173433303833, timestamp=1667424787.0472581) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5918884
-No: 4 GFLOPS: 0.00/10.07 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9866393
+No: 6 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -936,9 +938,13 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6114494
-No: 5 GFLOPS: 17.37/17.37 result: MeasureResult(costs=(0.013326816111111112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.785916328430176, timestamp=1667424792.0364811) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3174125
-No: 6 GFLOPS: 0.00/17.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5574085
+No: 7 GFLOPS: 18.27/259.24 result: MeasureResult(costs=(0.012669486272727272,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.958767414093018, timestamp=1667434056.0623786) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8596967
+No: 8 GFLOPS: 41.34/259.24 result: MeasureResult(costs=(0.005600369722222223,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.537811517715454, timestamp=1667434056.761774) [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2517863
+No: 9 GFLOPS: 8.37/259.24 result: MeasureResult(costs=(0.027643880750000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.271986484527588, timestamp=1667434066.119886) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8219272
+No: 10 GFLOPS: 3.63/259.24 result: MeasureResult(costs=(0.0637336005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.639305830001831, timestamp=1667434067.3300345) [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9688708
+No: 11 GFLOPS: 232.03/259.24 result: MeasureResult(costs=(0.0009977095940594059,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.32674503326416, timestamp=1667434067.9675095) [('tile_f', [-1, 1, 16, 8]), ('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, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9361158
+No: 12 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1060,8 +1066,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5532106
-No: 7 GFLOPS: 0.00/17.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3345506
+No: 13 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1183,9 +1189,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,885080
-No: 8 GFLOPS: 119.94/119.94 result: MeasureResult(costs=(0.0019302159807692307,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1279845237731934, timestamp=1667424794.7434168) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3293114
-No: 9 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,542252
+No: 14 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1307,8 +1312,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2764456
-No: 10 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9260437
+No: 15 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1430,8 +1435,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2351882
-No: 11 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4254013
+No: 16 GFLOPS: 65.45/259.24 result: MeasureResult(costs=(0.003537009655172414,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3549180030822754, timestamp=1667434069.558425) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1451278
+No: 17 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1553,8 +1559,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7916676
-No: 12 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,526536
+No: 18 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1676,8 +1682,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2901850
-No: 13 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8255852
+No: 19 GFLOPS: 0.00/259.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1799,624 +1805,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10296317
-No: 14 GFLOPS: 0.00/119.94 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4606271
-No: 15 GFLOPS: 2.48/119.94 result: MeasureResult(costs=(0.093395912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.356995105743408, timestamp=1667424797.5311258) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,508434
-No: 16 GFLOPS: 403.73/403.73 result: MeasureResult(costs=(0.0005734048857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.129640817642212, timestamp=1667424798.1717036) [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2013011
-No: 17 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2597932
-No: 18 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3377019
-No: 19 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4622637
-No: 20 GFLOPS: 0.00/403.73 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:391
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:377
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:272
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- 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 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9482753
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2489652
+No: 20 GFLOPS: 119.08/259.24 result: MeasureResult(costs=(0.0019440998103448276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1154589653015137, timestamp=1667434071.932883) [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8947438
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2455,9 +1845,9 @@ 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2013011
+[('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3558974
Finish loading 20 records
-Time cost of this operator: 0.000986
+Time cost of this operator: 0.001260
</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 5bb217ab6a..b04f914108 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -595,10 +595,10 @@ 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 311.8 98.718 (1, 2, 10, 10, 3) 2 1 [311.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.087 0.977 (1, 6, 10, 10) 1 1 [3.087]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.304 (1, 1, 10, 10, 3) 1 1 [0.961]
-Total_time - 315.848 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.5 98.725 (1, 2, 10, 10, 3) 2 1 [312.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.961 (1, 6, 10, 10) 1 1 [3.042]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.994 0.314 (1, 1, 10, 10, 3) 1 1 [0.994]
+Total_time - 316.536 - - - - -
</pre></div>
</div>
</div>
@@ -649,10 +649,10 @@ 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 100.1 97.11 (1, 6, 10, 10, 1) 2 1 [100.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.002 1.942 (1, 6, 10, 10) 1 1 [2.002]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.948 (1, 1, 10, 10, 3) 1 1 [0.978]
-Total_time - 103.079 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.3 97.432 (1, 6, 10, 10, 1) 2 1 [103.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.669 (1, 6, 10, 10) 1 1 [1.77]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.899 (1, 1, 10, 10, 3) 1 1 [0.953]
+Total_time - 106.023 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 2a4fda6328..d1399a887d 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -529,7 +529,7 @@ 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/tmpr703tk5r/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp_he_bkvt/images/random'
</pre></div>
</div>
</div>
@@ -589,8 +589,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpr703tk5r/images/target contains 8144 images
-/tmp/tmpr703tk5r/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], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp_he_bkvt/images/target contains 8144 images
+/tmp/tmp_he_bkvt/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -702,13 +702,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2159 - accuracy: 0.9237 - val_loss: 0.2209 - val_accuracy: 0.9256 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.2151 - accuracy: 0.9280 - val_loss: 0.1232 - val_accuracy: 0.9520 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0994 - accuracy: 0.9605 - val_loss: 0.1332 - val_accuracy: 0.9562 - 44s/epoch - 134ms/step
+328/328 - 44s - loss: 0.0990 - accuracy: 0.9645 - val_loss: 0.1204 - val_accuracy: 0.9585 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0737 - accuracy: 0.9708 - val_loss: 0.1085 - val_accuracy: 0.9660 - 44s/epoch - 134ms/step
+328/328 - 43s - loss: 0.0641 - accuracy: 0.9764 - val_loss: 0.1628 - val_accuracy: 0.9592 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f697c4cf650>
+<keras.callbacks.History object at 0x7fcde4465990>
</pre></div>
</div>
</div>
@@ -970,7 +970,7 @@ 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 41.437 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 4.899 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 0d6f4c5394..45f9f95cf6 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>05:45.808</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:07.992</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:41.437</p></td>
+<td><p>05:04.899</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:51.827</p></td>
+<td><p>00:50.811</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.624</p></td>
+<td><p>00:08.442</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.917</p></td>
+<td><p>00:03.838</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index b448a7a5b8..929608333e 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.253</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.900</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:33.090</p></td>
+<td><p>00:32.487</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>00:10.531</p></td>
+<td><p>00:09.869</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>00:01.626</p></td>
+<td><p>00:01.537</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 fc411d9826..31140975d6 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 0x7f692599ab00>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fcd855175f0>
</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 026f2b91c1..72fdb27e0e 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>00:06.511</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.366</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.082</p></td>
+<td><p>00:06.070</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>00:01.062</p></td>
+<td><p>00:00.959</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>00:00.583</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>00:00.567</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>00:00.118</p></td>
+<td><p>00:00.117</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.052</p></td>
+<td><p>00:00.049</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 9fd55d9b1e..76c1eb36fd 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -590,7 +590,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpnddzkjp_/input0.cc'\nsource_filename = \"/tmp/tmpnddzkjp_/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpvharewve/input0.cc'\nsource_filename = \"/tmp/tmpvharewve/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 2737666945..f1aa99cec2 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index c8e2506c40..2452bb5380 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/d261fa883/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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 7040c12b2b..d3752f1d02 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/d261fa883/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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 5419233780..9deab07d6c 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/d261fa883/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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 0ae7dc48ec..309177d4db 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/d261fa883/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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 aa5046bc2a..1247cf7fb0 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/d261fa883/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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 049cb5b35b..dac6fdf96e 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/d261fa883/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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/d261fa883/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/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 ee31e0780f..178c6c3da7 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/d261fa883/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/ff6aaeb12/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
... 2474 lines suppressed ...