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 2022/11/09 00:13:06 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@16bb1a6c2ee7a8f68f15ab8710588c75880e0dd5)
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 81e895c88a deploying docs (apache/tvm@16bb1a6c2ee7a8f68f15ab8710588c75880e0dd5)
81e895c88a is described below
commit 81e895c88af0f4129cb276235c68f5cdc5ec5f01
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Nov 9 00:12:58 2022 +0000
deploying docs (apache/tvm@16bb1a6c2ee7a8f68f15ab8710588c75880e0dd5)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 314727 -> 335230 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23008 -> 23974 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 | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2597 +++++++++++++-------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 221 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 205 +-
.../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 | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 4 +-
.../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 | 55 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
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 | 11 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 40 +-
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 | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2597 +++++++++++++-------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 221 +-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 205 +-
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/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 4 +-
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 | 273 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
125 files changed, 4700 insertions(+), 2943 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 44d42e7073..4730ebaecb 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..4f63c99e35 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 d75a6d614d..a09da5ef46 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 9.296 seconds)
+ **Total running time of the script:** ( 1 minutes 12.050 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 98ebbdbd9d..74b731c412 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 954ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 970ms/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 6c2b4b0807..9c30b73ad1 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.zip7e9e7920-d32c-45ff-980e-29907c60a058 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc644c5f8-48a3-4006-93ef-e033773d2bad 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 1e2279e386..bf992bbe52 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]
32%|###1 | 13.2M/41.5M [00:00<00:00, 132MB/s]
62%|######2 | 25.8M/41.5M [00:00<00:00, 87.5MB/s]
84%|########4 | 34.9M/41.5M [00:00<00:00, 55.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 69.2MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 61.1MB/s]
38%|###7 | 15.6M/41.5M [00:00<00:00, 70.8MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.2MB/s]
69%|######8 | 28.6M/41.5M [00:00<00:00, 54.0MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 42.6MB/s]
93%|#########2| 38.5M/41.5M [00:00<00:00, 43.0MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 47.6MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index a8ee69f186..40ca6cdd5f 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]
27%|##7 | 12.3M/44.7M [00:00<00:00, 129MB/s]
55%|#####4 | 24.6M/44.7M [00:00<00:00, 109MB/s]
79%|#######8 | 35.1M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
23%|##2 | 10.1M/44.7M [00:00<00:00, 53.6MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 87.2MB/s]
74%|#######4 | 33.2M/44.7M [00:00<00:00, 64.1MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 67.5MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 68.4MB/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 be04634a6a..d9f175f6b9 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 11.488 seconds)
+ **Total running time of the script:** ( 1 minutes 11.507 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 8c69fa6f4c..e497892b6b 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
=================
-**05:46.583** total execution time for **how_to_compile_models** files:
+**05:50.997** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.488 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:12.050 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.296 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.507 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.777 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.114 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.579 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.630 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.285 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.261 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.691 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.739 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.748 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.956 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.020 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.499 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.618 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.366 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.386 | 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 0b10686776..65d9523273 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)
- 16.2452 16.2177 17.0322 15.6039 0.4963
+ 16.3597 16.4060 16.8215 15.7883 0.4284
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 0b87357a30..417df6e7ea 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]
8%|7 | 13.5M/170M [00:00<00:01, 141MB/s]
16%|#5 | 27.0M/170M [00:00<00:01, 113MB/s]
22%|##2 | 38.1M/170M [00:00<00:01, 107MB/s]
29%|##8 | 48.5M/170M [00:00<00:01, 102MB/s]
35%|###4 | 58.7M/170M [00:00<00:01, 104MB/s]
40%|#### | 68.7M/170M [00:00<00:01, 103MB/s]
46%|####6 | 78.5M/170M [00:00<00:00, 102MB/s]
52%|#####1 | 88.3M/170M [00:00<00:00, 101MB/s]
58%|#####7 | 98.0M/170M [00:00<00:00, 101MB/s]
63%|######3 | 108M/170M [00:01<00:00, 100MB/s]
69%|######9 | 117M/170M [00:01<00:00, 101MB/s]
75%|#######4 | 127M/170M [00:01<00:00, 101MB/s]
80%|######## | 137M/170M [00:01<00:00, 99.4MB/s]
86%|########6 | 146M/170M [00:01<00:00, 101MB/s]
92%|#########1| 156M/170M [00:01<00:00, 101MB/s]
98%|#########7| 166M/170M [00:01<00:00, 100MB/s]
100%|##########| 170M/170M [00:01<00:00, 102MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:03, 47.6MB/s]
8%|8 | 14.3M/170M [00:00<00:03, 53.7MB/s]
12%|#1 | 19.6M/170M [00:00<00:03, 42.8MB/s]
15%|#5 | 26.1M/170M [00:00<00:03, 49.7MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 46.3MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 50.8MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 56.3MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 73.7MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 70.4MB/s]
48%|####8 | 82.1M/170M [00:01<00:01, 74.2MB/s]
52%|#####2 | 89.1M/170M [00:01<00:01, 71.3MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 70.3MB/s]
60%|###### | 103M/170M [00:01<00:01, 68.3MB/s]
64%|######4 | 109M/170M [00:01<00:00, 63.9MB/s]
71%|####### | 120M/170M [00:01<00:00, 69.7MB/s]
79%|#######8 | 134M/170M [00:02<00:00, 88.9MB/s]
84%|########3 | 143M/170M [00:02<00:00, 84.5MB/s]
89%|########9 | 152M/170M [00:02<00:00, 76.5MB/s]
94%|#########4| 160M/170M [00:02<00:00, 69.6MB/s]
99%|#########8| 168M/170M [00:02<00:00, 68.6MB/s]
100%|##########| 170M/170M [00:02<00:00, 67.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -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 15.840 seconds)
+ **Total running time of the script:** ( 3 minutes 12.732 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 0b569c331e..2480fd4289 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]
60%|#####9 | 8.12M/13.6M [00:00<00:00, 77.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 108MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
63%|######3 | 8.59M/13.6M [00:00<00:00, 90.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 104MB/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)
- 90.5757 90.4862 93.7646 90.3663 0.3669
+ 90.4625 90.3304 92.9230 90.1025 0.4444
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.376 seconds)
+ **Total running time of the script:** ( 1 minutes 5.933 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 cd0951e365..877d30580e 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)
- 119.7653 119.6711 124.5059 118.6998 0.7190
+ 120.3298 120.2409 125.2988 119.4781 0.5993
@@ -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 33.832 seconds)
+ **Total running time of the script:** ( 2 minutes 31.670 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 6f1faae0ae..4559764513 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 17.550 seconds)
+ **Total running time of the script:** ( 1 minutes 26.444 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 98fa6cd393..2ca615d752 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]
5%|5 | 6777/132723 [00:00<00:01, 67761.66KB/s]
12%|#1 | 15316/132723 [00:00<00:01, 78127.72KB/s]
18%|#8 | 23934/132723 [00:00<00:01, 81799.25KB/s]
25%|##4 | 32571/132723 [00:00<00:01, 83601.05KB/s]
31%|###1 | 41226/132723 [00:00<00:01, 84662.24KB/s]
37%|###7 | 49768/132723 [00:00<00:00, 84916.11KB/s]
44%|####4 | 58425/132723 [00:00<00:00, 85449.00KB/s]
51%|##### | 67096/132723 [00:00<00:00, 85847.30KB/s]
57%|#####7 | 75849/132723 [00:00<00:00, 86369.70KB/s]
64%|######3 | 84513/132723 [00:01<00:00, 86451.83KB/s]
70%|####### | 93217/132723 [00:01<00:00, 86627.49KB/s]
77%|#######6 | 101880/132723 [00:01<00:00, 85832.19KB/s]
83%|########3 | 110652/132723 [00:01<00:00, 86397.41KB/s]
90%|########9 | 119345/132723 [00:01<00:00, 86555.09KB/s]
97%|#########6| 128084/132723 [00:01<00:00, 86803.61KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 85154.65KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 4964/132723 [00:00<00:02, 49635.79KB/s]
9%|9 | 12094/132723 [00:00<00:01, 62376.41KB/s]
14%|#4 | 19228/132723 [00:00<00:01, 66466.48KB/s]
20%|#9 | 26375/132723 [00:00<00:01, 68405.82KB/s]
25%|##5 | 33777/132723 [00:00<00:01, 70425.07KB/s]
31%|###1 | 41149/132723 [00:00<00:01, 71538.68KB/s]
37%|###6 | 48577/132723 [00:00<00:01, 72431.01KB/s]
42%|####2 | 56039/132723 [00:00<00:01, 73122.32KB/s]
48%|####7 | 63567/132723 [00:00<00:00, 73795.36KB/s]
53%|#####3 | 71000/132723 [00:01<00:00, 73957.47KB/s]
59%|#####9 | 78512/132723 [00:01<00:00, 74310.80KB/s]
65%|######4 | 86209/132723 [00:01<00:00, 75116.42KB/s]
71%|####### | 93721/132723 [00:01<00:00, 71919.47KB/s]
76%|#######6 | 101155/132723 [00:01<00:00, 72626.41KB/s]
82%|########1 | 108823/132723 [00:01<00:00, 73820.89KB/s]
88%|########7
| 116479/132723 [00:01<00:00, 74631.02KB/s]
94%|#########3| 124138/132723 [00:01<00:00, 75212.02KB/s]
100%|#########9| 132158/132723 [00:01<00:00, 76696.21KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72772.46KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 2.662 seconds)
+ **Total running time of the script:** ( 3 minutes 0.093 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 a71efa3b93..cffe71b601 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:42.323** total execution time for **how_to_deploy_models** files:
+**12:43.530** 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``) | 03:15.840 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:12.732 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:02.662 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:00.093 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:33.832 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:31.670 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:17.550 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:26.444 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.376 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.933 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.823 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.850 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.649 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.631 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.586 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.172 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index bbc818da46..cb2d73f6a4 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.zip5e9b1990-ef6d-4452-89f7-cb1e62dc2570 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipddcd3805-d4ac-4f71-ac80-741cf80ee93b 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 fd61f67ef1..9cd5f21c9e 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
=================
-**00:47.105** total execution time for **how_to_extend_tvm** files:
+**00:46.584** 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``) | 00:43.664 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.245 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.401 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.323 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.009 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index c8d4daabae..0efb74125f 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: 6732us [6732us] (45.93%; 45.93%)
- FoldScaleAxis: 7924us [6us] (54.07%; 54.07%)
- FoldConstant: 7918us [1633us] (54.03%; 99.93%)
- InferType: 6285us [6285us] (42.88%; 79.37%)
+ InferType: 6612us [6612us] (46.52%; 46.52%)
+ FoldScaleAxis: 7600us [5us] (53.48%; 53.48%)
+ FoldConstant: 7595us [1522us] (53.44%; 99.93%)
+ InferType: 6073us [6073us] (42.73%; 79.96%)
@@ -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: 6355us [6355us] (44.45%; 44.45%)
- FoldScaleAxis: 7942us [5us] (55.55%; 55.55%)
- FoldConstant: 7938us [1631us] (55.52%; 99.94%)
- InferType: 6306us [6306us] (44.11%; 79.45%)
+ InferType: 6154us [6154us] (44.83%; 44.83%)
+ FoldScaleAxis: 7573us [5us] (55.17%; 55.17%)
+ FoldConstant: 7568us [1526us] (55.13%; 99.94%)
+ InferType: 6042us [6042us] (44.02%; 79.84%)
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 02db2511c2..ec9ef22722 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: 44.954753 ms
+ Convolution: 52.604576 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 9a8b89df26..7cbb43d24b 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: 10.586887 ms
+ conv2d with tensor core: 11.859827 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 b8e635c7bb..f188ab21d8 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: 0.018589
- Baseline: 3.342600
+ Numpy running time: 0.018560
+ Baseline: 3.432973
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.298713
+ Opt1: 0.301429
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.337551
+ Opt2: 0.336746
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.115560
+ Opt3: 0.116359
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109716
+ Opt4: 0.109505
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111788
+ Opt5: 0.112132
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147106
+ Opt6: 0.146623
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 4bf7ac966c..7d6435dfd6 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.573** total execution time for **how_to_optimize_operators** files:
+**00:34.985** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.130 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.377 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.374 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.471 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.069 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.137 | 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 914a1dd4ad..c4a494bd36 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
=================
-**08:58.752** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:16.563** 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``) | 05:33.283 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:46.350 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.897 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.131 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.856 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.524 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.392 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.791 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.019 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.999 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.048 | 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 7f37eaedfe..707f48bbf0 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
@@ -240,483 +240,1021 @@ 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;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [432]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[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[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [432], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 5), 27)) && (floormod((threadIdx.x_1 + 5), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 10), 27)) && (floormod((threadIdx.x_1 + 10), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 5), 9)) && (floormod((threadIdx.x_1 + 15), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 20), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 25), 27)) && (floormod((threadIdx.x_1 + 25), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 1), 9)) && (floormod((threadIdx.x_1 + 3), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 1), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 8), 27)) && (floormod((threadIdx.x_1 + 8), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)] [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 256)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 13), 27)) && (floormod((threadIdx.x_1 + 13), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 256), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 13), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 288)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 6), 9)) && (floormod((threadIdx.x_1 + 18), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 288), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 6), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 320)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 23), 27)) && (floormod((threadIdx.x_1 + 23), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 320), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 352)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 1), 27)) && (floormod((threadIdx.x_1 + 1), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 352), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)] [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 384)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 2), 9)) && (floormod((threadIdx.x_1 + 6), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 384), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 2), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 416)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 416), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 32), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 64), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 96)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 192), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 320), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 384), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 480), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 512), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 608), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 704), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 768), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 832), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 928), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 960), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 992), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1024), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1056), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1184), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1216), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1248), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1376), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1504), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1536), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1600), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1632), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1664), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1696), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1760), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1824), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1856), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1888), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1920), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1984), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2048), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2112), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2208), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2272), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2336), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2368), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2400), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2432), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2496), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2528), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2656), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2720), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2784), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2816), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2848), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2944), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2976), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3008), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3040), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3072), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3104), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3200), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3264), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3328), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3488), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3520), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3552), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3648), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3680), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3712), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3776), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3840), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3872), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3936), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4000), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4096), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4128), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4192), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4224), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4384), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4416), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4512), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ for (rc.outer.inner: int32, 0, 2) {
+ let cse_var_171: int32 = (rc.outer.inner*216)
+ let cse_var_170: int32 = (cse_var_171 + 99)
+ let cse_var_169: int32 = (cse_var_171 + 98)
+ let cse_var_168: int32 = (cse_var_171 + 97)
+ let cse_var_167: int32 = (cse_var_171 + 96)
+ let cse_var_166: int32 = (cse_var_171 + 95)
+ let cse_var_165: int32 = (cse_var_171 + 94)
+ let cse_var_164: int32 = (cse_var_171 + 93)
+ let cse_var_163: int32 = (cse_var_171 + 92)
+ let cse_var_162: int32 = (cse_var_171 + 91)
+ let cse_var_161: int32 = (cse_var_171 + 90)
+ let cse_var_160: int32 = (cse_var_171 + 9)
+ let cse_var_159: int32 = (cse_var_171 + 89)
+ let cse_var_158: int32 = (cse_var_171 + 88)
+ let cse_var_157: int32 = (cse_var_171 + 87)
+ let cse_var_156: int32 = (cse_var_171 + 86)
+ let cse_var_155: int32 = (cse_var_171 + 85)
+ let cse_var_154: int32 = (cse_var_171 + 84)
+ let cse_var_153: int32 = (cse_var_171 + 8)
+ let cse_var_152: int32 = (cse_var_171 + 77)
+ let cse_var_151: int32 = (cse_var_171 + 76)
+ let cse_var_150: int32 = (cse_var_171 + 75)
+ let cse_var_149: int32 = (cse_var_171 + 74)
+ let cse_var_148: int32 = (cse_var_171 + 73)
+ let cse_var_147: int32 = (cse_var_171 + 72)
+ let cse_var_146: int32 = (cse_var_171 + 71)
+ let cse_var_145: int32 = (cse_var_171 + 70)
+ let cse_var_144: int32 = (cse_var_171 + 7)
+ let cse_var_143: int32 = (cse_var_171 + 69)
+ let cse_var_142: int32 = (cse_var_171 + 68)
+ let cse_var_141: int32 = (cse_var_171 + 67)
+ let cse_var_140: int32 = (cse_var_171 + 66)
+ let cse_var_139: int32 = (cse_var_171 + 65)
+ let cse_var_138: int32 = (cse_var_171 + 64)
+ let cse_var_137: int32 = (cse_var_171 + 63)
+ let cse_var_136: int32 = (cse_var_171 + 62)
+ let cse_var_135: int32 = (cse_var_171 + 61)
+ let cse_var_134: int32 = (cse_var_171 + 60)
+ let cse_var_133: int32 = (cse_var_171 + 6)
+ let cse_var_132: int32 = (cse_var_171 + 59)
+ let cse_var_131: int32 = (cse_var_171 + 58)
+ let cse_var_130: int32 = (cse_var_171 + 57)
+ let cse_var_129: int32 = (cse_var_171 + 50)
+ let cse_var_128: int32 = (cse_var_171 + 5)
+ let cse_var_127: int32 = (cse_var_171 + 49)
+ let cse_var_126: int32 = (cse_var_171 + 48)
+ let cse_var_125: int32 = (cse_var_171 + 47)
+ let cse_var_124: int32 = (cse_var_171 + 46)
+ let cse_var_123: int32 = (cse_var_171 + 45)
+ let cse_var_122: int32 = (cse_var_171 + 44)
+ let cse_var_121: int32 = (cse_var_171 + 43)
+ let cse_var_120: int32 = (cse_var_171 + 42)
+ let cse_var_119: int32 = (cse_var_171 + 41)
+ let cse_var_118: int32 = (cse_var_171 + 40)
+ let cse_var_117: int32 = (cse_var_171 + 4)
+ let cse_var_116: int32 = (cse_var_171 + 39)
+ let cse_var_115: int32 = (cse_var_171 + 38)
+ let cse_var_114: int32 = (cse_var_171 + 37)
+ let cse_var_113: int32 = (cse_var_171 + 36)
+ let cse_var_112: int32 = (cse_var_171 + 35)
+ let cse_var_111: int32 = (cse_var_171 + 34)
+ let cse_var_110: int32 = (cse_var_171 + 33)
+ let cse_var_109: int32 = (cse_var_171 + 32)
+ let cse_var_108: int32 = (cse_var_171 + 31)
+ let cse_var_107: int32 = (cse_var_171 + 30)
+ let cse_var_106: int32 = (cse_var_171 + 3)
+ let cse_var_105: int32 = (cse_var_171 + 23)
+ let cse_var_104: int32 = (cse_var_171 + 22)
+ let cse_var_103: int32 = (cse_var_171 + 212)
+ let cse_var_102: int32 = (cse_var_171 + 211)
+ let cse_var_101: int32 = (cse_var_171 + 210)
+ let cse_var_100: int32 = (cse_var_171 + 21)
+ let cse_var_99: int32 = (cse_var_171 + 209)
+ let cse_var_98: int32 = (cse_var_171 + 208)
+ let cse_var_97: int32 = (cse_var_171 + 207)
+ let cse_var_96: int32 = (cse_var_171 + 206)
+ let cse_var_95: int32 = (cse_var_171 + 205)
+ let cse_var_94: int32 = (cse_var_171 + 204)
+ let cse_var_93: int32 = (cse_var_171 + 203)
+ let cse_var_92: int32 = (cse_var_171 + 202)
+ let cse_var_91: int32 = (cse_var_171 + 201)
+ let cse_var_90: int32 = (cse_var_171 + 200)
+ let cse_var_89: int32 = (cse_var_171 + 20)
+ let cse_var_88: int32 = (cse_var_171 + 199)
+ let cse_var_87: int32 = (cse_var_171 + 198)
+ let cse_var_86: int32 = (cse_var_171 + 197)
+ let cse_var_85: int32 = (cse_var_171 + 196)
+ let cse_var_84: int32 = (cse_var_171 + 195)
+ let cse_var_83: int32 = (cse_var_171 + 194)
+ let cse_var_82: int32 = (cse_var_171 + 193)
+ let cse_var_81: int32 = (cse_var_171 + 192)
+ let cse_var_80: int32 = (cse_var_171 + 19)
+ let cse_var_79: int32 = (cse_var_171 + 185)
+ let cse_var_78: int32 = (cse_var_171 + 184)
+ let cse_var_77: int32 = (cse_var_171 + 183)
+ let cse_var_76: int32 = (cse_var_171 + 182)
+ let cse_var_75: int32 = (cse_var_171 + 181)
+ let cse_var_74: int32 = (cse_var_171 + 180)
+ let cse_var_73: int32 = (cse_var_171 + 18)
+ let cse_var_72: int32 = (cse_var_171 + 179)
+ let cse_var_71: int32 = (cse_var_171 + 178)
+ let cse_var_70: int32 = (cse_var_171 + 177)
+ let cse_var_69: int32 = (cse_var_171 + 176)
+ let cse_var_68: int32 = (cse_var_171 + 175)
+ let cse_var_67: int32 = (cse_var_171 + 174)
+ let cse_var_66: int32 = (cse_var_171 + 173)
+ let cse_var_65: int32 = (cse_var_171 + 172)
+ let cse_var_64: int32 = (cse_var_171 + 171)
+ let cse_var_63: int32 = (cse_var_171 + 170)
+ let cse_var_62: int32 = (cse_var_171 + 17)
+ let cse_var_61: int32 = (cse_var_171 + 169)
+ let cse_var_60: int32 = (cse_var_171 + 168)
+ let cse_var_59: int32 = (cse_var_171 + 167)
+ let cse_var_58: int32 = (cse_var_171 + 166)
+ let cse_var_57: int32 = (cse_var_171 + 165)
+ let cse_var_56: int32 = (cse_var_171 + 16)
+ let cse_var_55: int32 = (cse_var_171 + 158)
+ let cse_var_54: int32 = (cse_var_171 + 157)
+ let cse_var_53: int32 = (cse_var_171 + 156)
+ let cse_var_52: int32 = (cse_var_171 + 155)
+ let cse_var_51: int32 = (cse_var_171 + 154)
+ let cse_var_50: int32 = (cse_var_171 + 153)
+ let cse_var_49: int32 = (cse_var_171 + 152)
+ let cse_var_48: int32 = (cse_var_171 + 151)
+ let cse_var_47: int32 = (cse_var_171 + 150)
+ let cse_var_46: int32 = (cse_var_171 + 15)
+ let cse_var_45: int32 = (cse_var_171 + 149)
+ let cse_var_44: int32 = (cse_var_171 + 148)
+ let cse_var_43: int32 = (cse_var_171 + 147)
+ let cse_var_42: int32 = (cse_var_171 + 146)
+ let cse_var_41: int32 = (cse_var_171 + 145)
+ let cse_var_40: int32 = (cse_var_171 + 144)
+ let cse_var_39: int32 = (cse_var_171 + 143)
+ let cse_var_38: int32 = (cse_var_171 + 142)
+ let cse_var_37: int32 = (cse_var_171 + 141)
+ let cse_var_36: int32 = (cse_var_171 + 140)
+ let cse_var_35: int32 = (cse_var_171 + 14)
+ let cse_var_34: int32 = (cse_var_171 + 139)
+ let cse_var_33: int32 = (cse_var_171 + 138)
+ let cse_var_32: int32 = (cse_var_171 + 131)
+ let cse_var_31: int32 = (cse_var_171 + 130)
+ let cse_var_30: int32 = (cse_var_171 + 13)
+ let cse_var_29: int32 = (cse_var_171 + 129)
+ let cse_var_28: int32 = (cse_var_171 + 128)
+ let cse_var_27: int32 = (cse_var_171 + 127)
+ let cse_var_26: int32 = (cse_var_171 + 126)
+ let cse_var_25: int32 = (cse_var_171 + 125)
+ let cse_var_24: int32 = (cse_var_171 + 124)
+ let cse_var_23: int32 = (cse_var_171 + 123)
+ let cse_var_22: int32 = (cse_var_171 + 122)
+ let cse_var_21: int32 = (cse_var_171 + 121)
+ let cse_var_20: int32 = (cse_var_171 + 120)
+ let cse_var_19: int32 = (cse_var_171 + 12)
+ let cse_var_18: int32 = (cse_var_171 + 119)
+ let cse_var_17: int32 = (cse_var_171 + 118)
+ let cse_var_16: int32 = (cse_var_171 + 117)
+ let cse_var_15: int32 = (cse_var_171 + 116)
+ let cse_var_14: int32 = (cse_var_171 + 115)
+ let cse_var_13: int32 = (cse_var_171 + 114)
+ let cse_var_12: int32 = (cse_var_171 + 113)
+ let cse_var_11: int32 = (cse_var_171 + 112)
+ let cse_var_10: int32 = (cse_var_171 + 111)
+ let cse_var_9: int32 = (cse_var_171 + 11)
+ let cse_var_8: int32 = (cse_var_171 + 104)
+ let cse_var_7: int32 = (cse_var_171 + 103)
+ let cse_var_6: int32 = (cse_var_171 + 102)
+ let cse_var_5: int32 = (cse_var_171 + 101)
+ let cse_var_4: int32 = (cse_var_171 + 100)
+ let cse_var_3: int32 = (cse_var_171 + 10)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_171]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 1)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 2)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 27)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 28)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 29)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 54)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 55)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 56)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 81)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 82)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 83)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 108)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 109)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 110)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 135)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 136)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 137)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 162)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 163)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 164)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 189)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 190)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 191)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_117]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_128]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_130]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_131]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_132]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_154]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_155]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_156]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_133]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_144]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_153]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_111]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_112]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_134]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_135]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_136]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_157]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_158]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_159]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_160]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_113]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_114]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_115]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_137]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_138]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_139]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_161]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_162]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_163]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_116]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_118]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_119]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_140]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_141]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_142]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_164]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_165]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_166]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_120]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_121]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_122]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_143]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_145]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_146]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_167]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_168]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_169]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_123]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_124]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_125]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_147]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_148]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_149]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_170]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_117]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_128]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_130]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_131]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_132]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_154]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_155]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_156]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_133]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_144]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_153]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_111]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_112]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_134]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_135]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_136]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_157]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_158]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_159]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_160]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_113]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_114]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_115]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_137]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_138]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_139]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_161]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_162]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_163]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_116]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_118]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_119]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_140]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_141]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_142]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_164]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_165]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_166]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_120]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_121]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_122]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_143]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_145]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_146]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_167]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_168]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_169]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_123]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_124]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_125]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_147]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_148]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_149]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_170]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_126]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_127]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_129]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_150]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_151]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_152]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_133]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_144]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_153]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_111]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_112]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_134]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_135]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_136]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_157]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_158]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_159]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_160]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_113]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_114]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_115]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_137]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_138]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_139]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_161]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_162]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_163]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_116]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_118]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_119]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_140]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_141]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_142]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_164]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_165]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_166]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_120]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_121]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_122]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_143]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_145]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_146]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_167]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_168]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_169]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_123]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_124]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_125]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_147]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_148]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_149]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_170]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_126]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_127]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_129]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_150]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_151]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_152]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 24)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 25)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 26)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 51)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 52)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 53)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 78)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 79)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 80)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 105)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 106)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 107)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 132)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 133)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 134)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 159)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 160)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 161)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 186)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 187)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 188)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 213)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 214)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 215)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 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[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
}
}
}
@@ -771,7 +1309,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.360 ms
+ Execution time of this operator: 0.266 ms
@@ -820,34 +1358,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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_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=32)
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_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=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- 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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
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_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=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
@@ -868,12 +1406,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=32)
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=32)
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)
@@ -893,10 +1431,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[432];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -904,420 +1442,679 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((3 <= ((((int)threadIdx.x) + 5) % 27)) && (((((int)threadIdx.x) + 5) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((3 <= ((((int)threadIdx.x) + 10) % 27)) && (((((int)threadIdx.x) + 10) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (((((int)threadIdx.x) / 3) + 5) % 9)) && (((((int)threadIdx.x) + 15) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 5) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((3 <= ((((int)threadIdx.x) + 25) % 27)) && (((((int)threadIdx.x) + 25) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (((((int)threadIdx.x) / 3) + 1) % 9)) && (((((int)threadIdx.x) + 3) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 1) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((3 <= ((((int)threadIdx.x) + 8) % 27)) && (((((int)threadIdx.x) + 8) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 27) * 49)) + ((((((int)threadIdx.x) + 8) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 256)] = (((((3 <= ((((int)threadIdx.x) + 13) % 27)) && (((((int)threadIdx.x) + 13) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 256) / 27) * 49)) + ((((((int)threadIdx.x) + 13) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 288)] = (((((1 <= (((((int)threadIdx.x) / 3) + 6) % 9)) && (((((int)threadIdx.x) + 18) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 288) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 6) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 320)] = (((((3 <= ((((int)threadIdx.x) + 23) % 27)) && (((((int)threadIdx.x) + 23) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 320) / 27) * 49)) + ((((((int)threadIdx.x) + 23) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 352)] = (((((3 <= ((((int)threadIdx.x) + 1) % 27)) && (((((int)threadIdx.x) + 1) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 352) / 27) * 49)) + ((((((int)threadIdx.x) + 1) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 384)] = (((((1 <= (((((int)threadIdx.x) / 3) + 2) % 9)) && (((((int)threadIdx.x) + 6) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 384) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 416)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 416) / 27) * 49)) + (((((int)threadIdx.x) + 11) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
}
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1216) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1312) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1376) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1408) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1504) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1600) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1632) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1664) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1696) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1760) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1888) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1984) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2048) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2208) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2272) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2336) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2368) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2432) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2528) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2560) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2656) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2816) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2848) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2944) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2976) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3008) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3040) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3072) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3104) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3200) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3264) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3328) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3392) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3424) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3488) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3520) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3552) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3648) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3680) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3712) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3776) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3872) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3936) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4000) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4096) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4160) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4192) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4288) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4384) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4576) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ __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 * 216)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 1)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 2)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 27)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 28)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 29)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 54)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 55)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 56)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 81)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 82)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 83)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 108)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 109)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 110)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 135)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 136)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 137)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 162)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 163)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 164)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 189)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 190)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 191)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 3)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 4)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 5)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 30)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 31)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 32)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 57)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 58)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 59)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 84)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 85)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 86)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 111)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 112)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 113)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 138)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 139)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 140)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 165)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 166)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 167)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 192)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 193)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 194)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 6)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 7)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 8)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 33)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 34)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 35)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 60)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 61)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 62)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 87)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 88)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 89)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 114)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 115)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 116)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 141)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 142)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 143)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 168)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 169)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 170)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 195)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 196)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 197)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 9)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 10)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 11)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 36)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 37)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 38)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 63)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 64)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 65)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 90)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 91)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 92)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 117)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 118)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 119)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 144)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 145)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 146)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 171)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 172)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 173)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 198)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 199)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 200)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 12)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 13)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 14)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 39)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 40)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 41)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 66)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 67)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 68)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 93)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 94)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 95)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 120)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 121)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 122)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 147)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 148)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 149)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 174)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 175)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 176)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 201)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 202)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 203)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 15)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 16)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 17)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 42)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 43)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 44)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 69)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 70)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 71)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 96)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 97)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 98)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 123)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 124)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 125)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 150)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 151)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 152)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 177)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 178)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 179)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 204)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 205)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 206)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 18)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 19)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 20)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 45)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 46)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 47)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 72)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 73)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 74)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 99)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 100)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 101)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 126)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 127)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 128)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 153)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 154)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 155)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 180)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 181)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 182)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 207)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 208)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 209)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 3)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 4)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 5)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 30)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 31)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 32)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 57)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 58)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 59)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 84)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 85)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 86)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 111)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 112)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 113)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 138)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 139)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 140)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 165)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 166)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 167)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 192)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 193)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 194)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 6)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 7)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 8)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 33)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 34)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 35)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 60)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 61)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 62)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 87)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 88)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 89)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 114)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 115)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 116)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 141)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 142)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 143)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 168)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 169)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 170)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 195)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 196)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 197)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 9)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 10)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 11)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 36)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 37)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 38)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 63)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 64)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 65)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 90)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 91)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 92)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 117)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 118)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 119)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 144)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 145)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 146)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 171)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 172)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 173)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 198)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 199)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 200)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 12)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 13)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 14)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 39)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 40)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 41)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 66)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 67)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 68)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 93)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 94)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 95)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 120)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 121)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 122)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 147)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 148)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 149)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 174)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 175)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 176)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 201)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 202)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 203)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 15)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 16)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 17)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 42)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 43)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 44)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 69)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 70)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 71)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 96)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 97)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 98)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 123)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 124)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 125)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 150)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 151)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 152)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 177)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 178)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 179)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 204)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 205)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 206)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 18)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 19)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 20)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 45)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 46)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 47)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 72)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 73)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 74)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 99)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 100)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 101)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 126)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 127)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 128)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 153)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 154)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 155)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 180)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 181)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 182)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 207)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 208)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 209)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 21)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 22)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 23)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 48)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 49)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 50)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 75)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 76)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 77)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 102)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 103)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 104)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 129)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 130)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 131)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 156)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 157)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 158)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 183)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 184)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 185)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 210)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 211)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 212)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 6)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 7)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 8)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 33)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 34)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 35)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 60)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 61)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 62)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 87)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 88)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 89)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 114)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 115)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 116)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 141)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 142)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 143)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 168)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 169)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 170)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 195)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 196)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 197)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 9)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 10)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 11)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 36)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 37)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 38)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 63)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 64)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 65)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 90)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 91)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 92)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 117)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 118)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 119)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 144)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 145)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 146)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 171)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 172)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 173)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 198)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 199)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 200)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 12)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 13)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 14)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 39)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 40)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 41)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 66)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 67)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 68)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 93)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 94)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 95)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 120)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 121)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 122)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 147)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 148)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 149)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 174)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 175)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 176)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 201)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 202)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 203)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 15)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 16)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 17)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 42)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 43)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 44)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 69)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 70)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 71)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 96)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 97)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 98)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 123)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 124)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 125)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 150)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 151)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 152)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 177)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 178)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 179)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 204)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 205)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 206)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 18)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 19)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 20)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 45)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 46)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 47)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 72)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 73)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 74)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 99)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 100)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 101)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 126)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 127)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 128)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 153)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 154)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 155)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 180)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 181)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 182)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 207)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 208)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 209)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 21)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 22)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 23)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 48)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 49)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 50)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 75)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 76)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 77)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 102)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 103)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 104)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 129)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 130)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 131)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 156)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 157)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 158)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 183)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 184)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 185)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 210)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 211)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 212)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 24)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 25)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 26)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 51)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 52)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 53)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 78)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 79)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 80)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 105)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 106)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 107)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 132)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 133)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 134)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 159)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 160)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 161)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 186)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 187)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 188)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 213)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 214)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 215)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
}
}
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ }
}
@@ -1378,7 +2175,7 @@ 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 33.283 seconds)
+ **Total running time of the script:** ( 5 minutes 46.350 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 50cba26ef3..aa529b1951 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)
- 8.2236 8.2198 8.2359 8.2150 0.0089
+ 8.1964 8.1980 8.2093 8.1820 0.0112
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.131 seconds)
+ **Total running time of the script:** ( 1 minutes 3.856 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 8a9a6ba802..c6e6da0ea8 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)
- 755.0832 754.4683 758.7039 752.0773 2.7400
+ 760.4773 760.9756 761.2818 759.1745 0.9296
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.024 seconds)
+ **Total running time of the script:** ( 1 minutes 32.897 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 c624178c76..df731be34e 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
@@ -386,32 +386,217 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[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
+ compute_5[(cse_var_1 + 32)] = 0f32
+ compute_5[(cse_var_1 + 33)] = 0f32
+ compute_5[(cse_var_1 + 34)] = 0f32
+ compute_5[(cse_var_1 + 35)] = 0f32
+ compute_5[(cse_var_1 + 36)] = 0f32
+ compute_5[(cse_var_1 + 37)] = 0f32
+ compute_5[(cse_var_1 + 38)] = 0f32
+ compute_5[(cse_var_1 + 39)] = 0f32
+ compute_5[(cse_var_1 + 40)] = 0f32
+ compute_5[(cse_var_1 + 41)] = 0f32
+ compute_5[(cse_var_1 + 42)] = 0f32
+ compute_5[(cse_var_1 + 43)] = 0f32
+ compute_5[(cse_var_1 + 44)] = 0f32
+ compute_5[(cse_var_1 + 45)] = 0f32
+ compute_5[(cse_var_1 + 46)] = 0f32
+ compute_5[(cse_var_1 + 47)] = 0f32
+ compute_5[(cse_var_1 + 64)] = 0f32
+ compute_5[(cse_var_1 + 65)] = 0f32
+ compute_5[(cse_var_1 + 66)] = 0f32
+ compute_5[(cse_var_1 + 67)] = 0f32
+ compute_5[(cse_var_1 + 68)] = 0f32
+ compute_5[(cse_var_1 + 69)] = 0f32
+ compute_5[(cse_var_1 + 70)] = 0f32
+ compute_5[(cse_var_1 + 71)] = 0f32
+ compute_5[(cse_var_1 + 72)] = 0f32
+ compute_5[(cse_var_1 + 73)] = 0f32
+ compute_5[(cse_var_1 + 74)] = 0f32
+ compute_5[(cse_var_1 + 75)] = 0f32
+ compute_5[(cse_var_1 + 76)] = 0f32
+ compute_5[(cse_var_1 + 77)] = 0f32
+ compute_5[(cse_var_1 + 78)] = 0f32
+ compute_5[(cse_var_1 + 79)] = 0f32
+ compute_5[(cse_var_1 + 96)] = 0f32
+ compute_5[(cse_var_1 + 97)] = 0f32
+ compute_5[(cse_var_1 + 98)] = 0f32
+ compute_5[(cse_var_1 + 99)] = 0f32
+ compute_5[(cse_var_1 + 100)] = 0f32
+ compute_5[(cse_var_1 + 101)] = 0f32
+ compute_5[(cse_var_1 + 102)] = 0f32
+ compute_5[(cse_var_1 + 103)] = 0f32
+ compute_5[(cse_var_1 + 104)] = 0f32
+ compute_5[(cse_var_1 + 105)] = 0f32
+ compute_5[(cse_var_1 + 106)] = 0f32
+ compute_5[(cse_var_1 + 107)] = 0f32
+ compute_5[(cse_var_1 + 108)] = 0f32
+ compute_5[(cse_var_1 + 109)] = 0f32
+ compute_5[(cse_var_1 + 110)] = 0f32
+ compute_5[(cse_var_1 + 111)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ let cse_var_67: int32 = (i.outer.inner*1024)
+ let cse_var_66: int32 = (elem_idx*16)
+ let cse_var_65: int32 = (cse_var_1 + 99)
+ let cse_var_64: int32 = (cse_var_1 + 98)
+ let cse_var_63: int32 = (cse_var_1 + 97)
+ let cse_var_62: int32 = (cse_var_1 + 96)
+ let cse_var_61: int32 = (cse_var_1 + 9)
+ let cse_var_60: int32 = (cse_var_1 + 8)
+ let cse_var_59: int32 = (cse_var_1 + 79)
+ let cse_var_58: int32 = (cse_var_1 + 78)
+ let cse_var_57: int32 = (cse_var_1 + 77)
+ let cse_var_56: int32 = (cse_var_1 + 76)
+ let cse_var_55: int32 = (cse_var_1 + 75)
+ let cse_var_54: int32 = (cse_var_1 + 74)
+ let cse_var_53: int32 = (cse_var_1 + 73)
+ let cse_var_52: int32 = (cse_var_1 + 72)
+ let cse_var_51: int32 = (cse_var_1 + 71)
+ let cse_var_50: int32 = (cse_var_1 + 70)
+ let cse_var_49: int32 = (cse_var_1 + 7)
+ let cse_var_48: int32 = (cse_var_1 + 69)
+ let cse_var_47: int32 = (cse_var_1 + 68)
+ let cse_var_46: int32 = (cse_var_1 + 67)
+ let cse_var_45: int32 = (cse_var_1 + 66)
+ let cse_var_44: int32 = (cse_var_1 + 65)
+ let cse_var_43: int32 = (cse_var_1 + 64)
+ let cse_var_42: int32 = (cse_var_1 + 6)
+ let cse_var_41: int32 = (cse_var_1 + 5)
+ let cse_var_40: int32 = (cse_var_1 + 47)
+ let cse_var_39: int32 = (cse_var_1 + 46)
+ let cse_var_38: int32 = (cse_var_1 + 45)
+ let cse_var_37: int32 = (cse_var_1 + 44)
+ let cse_var_36: int32 = (cse_var_1 + 43)
+ let cse_var_35: int32 = (cse_var_1 + 42)
+ let cse_var_34: int32 = (cse_var_1 + 41)
+ let cse_var_33: int32 = (cse_var_1 + 40)
+ let cse_var_32: int32 = (cse_var_1 + 4)
+ let cse_var_31: int32 = (cse_var_1 + 39)
+ let cse_var_30: int32 = (cse_var_1 + 38)
+ let cse_var_29: int32 = (cse_var_1 + 37)
+ let cse_var_28: int32 = (cse_var_1 + 36)
+ let cse_var_27: int32 = (cse_var_1 + 35)
+ let cse_var_26: int32 = (cse_var_1 + 34)
+ let cse_var_25: int32 = (cse_var_1 + 33)
+ let cse_var_24: int32 = (cse_var_1 + 32)
+ let cse_var_23: int32 = (cse_var_1 + 3)
+ let cse_var_22: int32 = (cse_var_1 + 2)
+ let cse_var_21: int32 = (cse_var_1 + 15)
+ let cse_var_20: int32 = (cse_var_1 + 14)
+ let cse_var_19: int32 = (cse_var_1 + 13)
+ let cse_var_18: int32 = (cse_var_1 + 12)
+ let cse_var_17: int32 = (cse_var_1 + 111)
+ let cse_var_16: int32 = (cse_var_1 + 110)
+ let cse_var_15: int32 = (cse_var_1 + 11)
+ let cse_var_14: int32 = (cse_var_1 + 109)
+ let cse_var_13: int32 = (cse_var_1 + 108)
+ let cse_var_12: int32 = (cse_var_1 + 107)
+ let cse_var_11: int32 = (cse_var_1 + 106)
+ let cse_var_10: int32 = (cse_var_1 + 105)
+ let cse_var_9: int32 = (cse_var_1 + 104)
+ let cse_var_8: int32 = (cse_var_1 + 103)
+ let cse_var_7: int32 = (cse_var_1 + 102)
+ let cse_var_6: int32 = (cse_var_1 + 101)
+ let cse_var_5: int32 = (cse_var_1 + 100)
+ let cse_var_4: int32 = (cse_var_1 + 10)
+ let cse_var_3: int32 = (cse_var_1 + 1)
+ {
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
- }
+ let cse_var_68: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -467,7 +652,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.634 ms
+ Execution time of this operator: 3.028 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 cb45e95a73..c04c31b9de 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:35.180** total execution time for **how_to_tune_with_autotvm** files:
+**00:36.592** 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``) | 00:35.145 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:36.555 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
++--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 25877968d4..465ef9d6c2 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -387,7 +387,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1127076
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5936006
No: 2 GFLOPS: 0.00/0.00 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)
@@ -510,7 +510,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6215972
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5966431
No: 3 GFLOPS: 0.00/0.00 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)
@@ -633,7 +633,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3045668
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5553765
No: 4 GFLOPS: 0.00/0.00 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)
@@ -756,9 +756,9 @@ 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, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6221353
- No: 5 GFLOPS: 47.85/47.85 result: MeasureResult(costs=(0.004837766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6264150142669678, timestamp=1667942409.181963) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2592560
- No: 6 GFLOPS: 0.00/47.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2903595
+ No: 5 GFLOPS: 363.62/363.62 result: MeasureResult(costs=(0.0006366531333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8916919231414795, timestamp=1667947565.4115362) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9530840
+ No: 6 GFLOPS: 0.00/363.62 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
@@ -880,9 +880,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10210354
- No: 7 GFLOPS: 52.95/52.95 result: MeasureResult(costs=(0.004371859304347826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6112711429595947, timestamp=1667942410.7586637) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 7, 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', 1500), ('unroll_explicit', 0)],None,4936373
- No: 8 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2542109
+ No: 7 GFLOPS: 193.97/363.62 result: MeasureResult(costs=(0.0011935006592592593,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7467830181121826, timestamp=1667947566.387904) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1891640
+ No: 8 GFLOPS: 3.89/363.62 result: MeasureResult(costs=(0.05947156125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2675788402557373, timestamp=1667947567.504721) [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,50272
+ No: 9 GFLOPS: 0.00/363.62 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
@@ -1004,8 +1005,8 @@ 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, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8634708
- No: 9 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ 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, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8082442
+ No: 10 GFLOPS: 0.00/363.62 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
@@ -1127,8 +1128,8 @@ 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, 16, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,339284
- No: 10 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1285173
+ No: 11 GFLOPS: 0.00/363.62 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
@@ -1250,8 +1251,8 @@ 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, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8322319
- No: 11 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,419124
+ No: 12 GFLOPS: 0.00/363.62 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
@@ -1373,9 +1374,9 @@ 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, 32, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,510697
- No: 12 GFLOPS: 8.74/52.95 result: MeasureResult(costs=(0.0264729595,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.278751850128174, timestamp=1667942419.2637608) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4999301
- No: 13 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10199016
+ No: 13 GFLOPS: 2.07/363.62 result: MeasureResult(costs=(0.11171890999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.094568967819214, timestamp=1667947570.947638) [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3136183
+ No: 14 GFLOPS: 0.00/363.62 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
@@ -1497,8 +1498,8 @@ 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6832781
- No: 14 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4996092
+ No: 15 GFLOPS: 0.00/363.62 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
@@ -1620,8 +1621,8 @@ 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, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4994568
- No: 15 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,116374
+ No: 16 GFLOPS: 0.00/363.62 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
@@ -1743,9 +1744,8 @@ 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, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3818192
- No: 16 GFLOPS: 2.24/52.95 result: MeasureResult(costs=(0.10320736675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.392850637435913, timestamp=1667942421.8846374) [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5349706
- No: 17 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10012317
+ No: 17 GFLOPS: 0.00/363.62 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
@@ -1867,8 +1867,26 @@ 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, 256, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5579739
- No: 18 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,407077
+ No: 18 GFLOPS: 0.00/363.62 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8807709
+ No: 19 GFLOPS: 0.00/363.62 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
@@ -1990,8 +2008,8 @@ 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, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1856760
- No: 19 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2505608
+ No: 20 GFLOPS: 0.00/363.62 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
@@ -2113,130 +2131,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7578505
- No: 20 GFLOPS: 0.00/52.95 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:388
- 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:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 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:388
- 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:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 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, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1065067
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8110720
@@ -2291,9 +2186,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 7, 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', 1500), ('unroll_explicit', 0)],None,4936373
+ [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9530840
Finish loading 20 records
- Time cost of this operator: 0.004712
+ Time cost of this operator: 0.000914
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 e8b6b4e214..8b567805e3 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 309.8 98.64 (1, 2, 10, 10, 3) 2 1 [309.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.141 1.0 (1, 6, 10, 10) 1 1 [3.141]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.13 0.36 (1, 1, 10, 10, 3) 1 1 [1.13]
- Total_time - 314.071 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.1 98.715 (1, 2, 10, 10, 3) 2 1 [311.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.978 (1, 6, 10, 10) 1 1 [3.082]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.308 (1, 1, 10, 10, 3) 1 1 [0.969]
+ Total_time - 315.151 - - - - -
@@ -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 136.7 98.111 (1, 6, 10, 10, 1) 2 1 [136.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.775 1.274 (1, 6, 10, 10) 1 1 [1.775]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.857 0.615 (1, 3, 10, 10, 1) 1 1 [0.857]
- Total_time - 139.332 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.503 (1, 6, 10, 10, 1) 2 1 [102.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.684 (1, 6, 10, 10) 1 1 [1.773]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.856 0.813 (1, 3, 10, 10, 1) 1 1 [0.856]
+ Total_time - 105.33 - - - - -
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 a779ab88d2..1c0ada0e75 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/tmpoh3r_kju/images/random'
+ '/tmp/tmps1or2jlt/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: [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
: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/tmpoh3r_kju/images/target contains 8144 images
- /tmp/tmpoh3r_kju/images/random contains 5000 images
+ /tmp/tmps1or2jlt/images/target contains 8144 images
+ /tmp/tmps1or2jlt/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: 0.2316 - accuracy: 0.9163 - val_loss: 0.1270 - val_accuracy: 0.9603 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2297 - accuracy: 0.9187 - val_loss: 0.1226 - val_accuracy: 0.9634 - 47s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.1021 - accuracy: 0.9614 - val_loss: 0.1203 - val_accuracy: 0.9664 - 44s/epoch - 134ms/step
+ 328/328 - 43s - loss: 0.0974 - accuracy: 0.9650 - val_loss: 0.1075 - val_accuracy: 0.9668 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0670 - accuracy: 0.9762 - val_loss: 0.1376 - val_accuracy: 0.9588 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0655 - accuracy: 0.9754 - val_loss: 0.1182 - val_accuracy: 0.9581 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7fdfa469b510>
+ <keras.callbacks.History object at 0x7efb7c131cd0>
@@ -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 33.541 seconds)
+ **Total running time of the script:** ( 4 minutes 18.321 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 21c6109b9c..3bd8ee7921 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
=================
-**05:34.359** total execution time for **how_to_work_with_microtvm** files:
+**05:20.260** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:33.541 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:18.321 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:48.920 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.126 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.204 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.927 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.692 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.884 | 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 2dc4d84d19..ee4df0bd0e 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.473** total execution time for **how_to_work_with_relay** files:
+**00:44.249** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.796 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.502 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.137 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.349 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.533 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.391 | 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 563bd71572..f91e60c89d 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 0x7fdf48c11050>
+ <function my_cuda_math_rule at 0x7efb7c4787a0>
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 84b6640bf5..bed8b21f1d 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
=================
-**00:06.457** total execution time for **how_to_work_with_schedules** files:
+**00:07.514** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.161 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.079 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.977 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.065 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.588 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.540 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.569 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.124 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.048 | 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 92df80eb5b..f4edaabcb4 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/tmp22fhpqe4/input0.cc'\nsource_filename = \"/tmp/tmp22fhpqe4/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/tmp362bexjz/input0.cc'\nsource_filename = \"/tmp/tmp362bexjz/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 5858c0276b..cd1d64950a 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
=================
-**00:26.188** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.179** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.182 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.172 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 611c0e17c8..e5910d2604 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 29.22s!
+ resnet18_v1 inference graph built in 28.79s!
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 d17e403f31..2e978ce33d 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 19.64s!
+ yolov3-tiny inference graph built in 19.56s!
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 c7eb435da8..0abb619b75 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
=================
-**01:41.024** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.594** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.804 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.805 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.220 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.789 | 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 16cf6d017c..b25d016731 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
=================
-**00:03.128** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.144** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.692 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.436 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.452 | 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 38351980d8..346d02eec6 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
=================
-**00:00.772** total execution time for **topic_vta_tutorials** files:
+**00:00.803** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.416 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.430 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.356 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.374 | 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 4fb1979f30..7df0603878 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
-
- .T
-
-
@@ -333,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.755 ms
+ Execution time of this operator: 96.390 ms
@@ -451,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.689 seconds)
+ **Total running time of the script:** ( 1 minutes 34.822 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 16cb421058..ca5c4383fc 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: 3.89/3.89 result: MeasureResult(costs=(0.0690217308,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.291485071182251, timestamp=1667941050.0056775) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
- No: 2 GFLOPS: 12.89/12.89 result: MeasureResult(costs=(0.0208230942,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6630985736846924, timestamp=1667941050.5487902) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
- No: 3 GFLOPS: 12.06/12.89 result: MeasureResult(costs=(0.0222498284,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5042881965637207, timestamp=1667941051.8129568) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 4 GFLOPS: 11.64/12.89 result: MeasureResult(costs=(0.023062826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5833685398101807, timestamp=1667941052.3525486) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
- No: 5 GFLOPS: 1.43/12.89 result: MeasureResult(costs=(0.18794764960000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1370859146118164, timestamp=1667941055.6512854) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
- No: 6 GFLOPS: 1.29/12.89 result: MeasureResult(costs=(0.207392229,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4534623622894287, timestamp=1667941059.866785) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
- No: 7 GFLOPS: 3.95/12.89 result: MeasureResult(costs=(0.0680127194,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2719974517822266, timestamp=1667941061.8616188) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
- No: 8 GFLOPS: 10.62/12.89 result: MeasureResult(costs=(0.025269213000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6043543815612793, timestamp=1667941062.4720986) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.76/12.89 result: MeasureResult(costs=(0.1522073394,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5542361736297607, timestamp=1667941065.4680543) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
- No: 10 GFLOPS: 9.94/12.89 result: MeasureResult(costs=(0.027003497199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8826088905334473, timestamp=1667941066.0713854) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
+ No: 1 GFLOPS: 2.34/2.34 result: MeasureResult(costs=(0.11481608940000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0053610801696777, timestamp=1667946187.796037) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
+ No: 2 GFLOPS: 1.89/2.34 result: MeasureResult(costs=(0.14230325419999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4249730110168457, timestamp=1667946191.0005813) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+ No: 3 GFLOPS: 2.79/2.79 result: MeasureResult(costs=(0.0961973486,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.674245834350586, timestamp=1667946192.7048013) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
+ No: 4 GFLOPS: 1.61/2.79 result: MeasureResult(costs=(0.1668141222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8033082485198975, timestamp=1667946196.2931778) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+ No: 5 GFLOPS: 8.03/8.03 result: MeasureResult(costs=(0.0334157078,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7658829689025879, timestamp=1667946197.1736145) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
+ No: 6 GFLOPS: 11.65/11.65 result: MeasureResult(costs=(0.023034349399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5698938369750977, timestamp=1667946197.711672) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+ No: 7 GFLOPS: 10.48/11.65 result: MeasureResult(costs=(0.025620343,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5554769039154053, timestamp=1667946199.0480788) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 8 GFLOPS: 12.21/12.21 result: MeasureResult(costs=(0.021984444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5655324459075928, timestamp=1667946199.6096277) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+ No: 9 GFLOPS: 14.33/14.33 result: MeasureResult(costs=(0.018727824400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4793386459350586, timestamp=1667946200.202289) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+ No: 10 GFLOPS: 9.10/14.33 result: MeasureResult(costs=(0.029496407199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6413588523864746, timestamp=1667946200.8372824) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index f7c1f9d87e..94925000be 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': 516.7291401700004, 'median': 517.3745978499994, 'std': 2.3085657145066754}
+ {'mean': 513.475046199992, 'median': 514.1611493499568, 'std': 3.162537198510625}
@@ -554,29 +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: 17.55/ 17.70 GFLOPS | Progress: (4/20) | 10.34 s
[Task 1/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (8/20) | 13.47 s
[Task 1/25] Current/Best: 17.86/ 19.01 GFLOPS | Progress: (12/20) | 16.48 s
[Task 1/25] Current/Best: 13.62/ 19.01 GFLOPS | Progress: (16/20) | 18.77 s
[Task 1/25] Current/Best: 22.77/ 23.03 GFLOPS | Progress: (20/20) | 20.83 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 8.75/ 11.50 GFLOPS | Progress: (4/20) | 2.62 s
[Task 2/25] Current/Best: 16.45/ 16.45 GFLOPS | Progress: (8/20) | 4.22 s
[Task 2/25] Current/Best: 12.40/ 16.45 GFLOPS | Progress: (12/20) | 5.44 s
[Task 2/25] Current/Best: 3.35/ 16.45 GFLOPS | Progress: (16/20) | 6.77 s
[Task 2/25] Current/Best: 8.93/ 22.44 GFLOPS | Progress: (20/20) | 8.01 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 9.31/ 14.76 GFLOPS | Progress: (4/20) | 3.73 s
[Task 3/25] Current/Best: 14.58/ 16.90 GFLOPS | Progress: (8/20) | 5.72 s
[Task 3/25] Current/Best: 15.30/ 16.90 GFLOPS | Progress: (12/20) | 7.75 s
[Task 3/25] Current/Best: 3.14/ 16.90 GFLOPS | Progress: (16/20) | 10.22 s
[Task 3/25] Current/Best: 3.20/ 16.90 GFLOPS | Progress: (20/20) | 12.59 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 16.60/ 16.60 GFLOPS | Progress: (4/20) | 3.63 s
[Task 4/25] Current/Best: 5.60/ 19.02 GFLOPS | Progress: (8/20) | 5.51 s
[Task 4/25] Current/Best: 12.60/ 19.02 GFLOPS | Progress: (12/20) | 7.05 s
[Task 4/25] Current/Best: 17.98/ 19.02 GFLOPS | Progress: (16/20) | 9.57 s
[Task 4/25] Current/Best: 5.57/ 19.02 GFLOPS | Progress: (20/20) | 11.49 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 12.10/ 16.11 GFLOPS | Progress: (4/20) | 3.70 s
[Task 5/25] Current/Best: 12.54/ 16.11 GFLOPS | Progress: (8/20) | 5.35 s
[Task 5/25] Current/Best: 12.24/ 18.95 GFLOPS | Progress: (12/20) | 7.27 s
[Task 5/25] Current/Best: 13.68/ 21.11 GFLOPS | Progress: (16/20) | 10.33 s
[Task 5/25] Current/Best: 23.54/ 23.54 GFLOPS | Progress: (20/20) | 11.85 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 16.27/ 16.27 GFLOPS | Progress: (4/20) | 3.93 s
[Task 6/25] Current/Best: 13.35/ 16.27 GFLOPS | Progress: (8/20) | 7.95 s
[Task 6/25] Current/Best: 14.34/ 17.71 GFLOPS | Progress: (12/20) | 9.88 s
[Task 6/25] Current/Best: 5.76/ 17.71 GFLOPS | Progress: (16/20) | 14.20 s
[Task 6/25] Current/Best: 3.26/ 23.11 GFLOPS | Progress: (20/20) | 16.74 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.93/ 15.93 GFLOPS | Progress: (4/20) | 3.43 s
[Task 7/25] Current/Best: 16.37/ 19.38 GFLOPS | Progress: (8/20) | 5.34 s
[Task 7/25] Current/Best: 5.42/ 19.38 GFLOPS | Progress: (12/20) | 7.52 s
[Task 7/25] Current/Best: 15.58/ 21.20 GFLOPS | Progress: (16/20) | 9.21 s
[Task 7/25] Current/Best: 9.43/ 21.20 GFLOPS | Progress: (20/20) | 12.09 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.63/ 10.79 GFLOPS | Progress: (4/20) | 9.97 s
[Task 8/25] Current/Best: 12.44/ 12.44 GFLOPS | Progress: (8/20) | 15.28 s
[Task 8/25] Current/Best: 13.01/ 13.16 GFLOPS | Progress: (12/20) | 18.05 s
[Task 8/25] Current/Best: 11.86/ 17.25 GFLOPS | Progress: (16/20) | 20.12 s
[Task 8/25] Current/Best: 18.64/ 22.16 GFLOPS | Progress: (20/20) | 21.67 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 9.83/ 18.40 GFLOPS | Progress: (4/20) | 4.11 s
[Task 9/25] Current/Best: 13.87/ 18.40 GFLOPS | Progress: (8/20) | 5.90 s
[Task 9/25] Current/Best: 13.58/ 21.54 GFLOPS | Progress: (12/20) | 7.39 s
[Task 9/25] Current/Best: 12.15/ 21.54 GFLOPS | Progress: (16/20) | 16.52 s
[Task 9/25] Current/Best: 6.46/ 21.54 GFLOPS | Progress: (20/20) | 21.58 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 8.11/ 16.94 GFLOPS | Progress: (4/20) | 3.49 s
[Task 10/25] Current/Best: 10.94/ 18.34 GFLOPS | Progress: (8/20) | 5.66 s
[Task 10/25] Current/Best: 20.21/ 20.21 GFLOPS | Progress: (12/20) | 7.44 s
[Task 10/25] Current/Best: 11.30/ 20.21 GFLOPS | Progress: (16/20) | 9.23 s
[Task 10/25] Current/Best: 6.63/ 20.21 GFLOPS | Progress: (20/20) | 10.82 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 13.68/ 19.75 GFLOPS | Progress: (4/20) | 4.54 s
[Task 11/25] Current/Best: 15.23/ 19.75 GFLOPS | Progress: (8/20) | 6.93 s
[Task 11/25] Current/Best: 21.00/ 21.00 GFLOPS | Progress: (12/20) | 9.10 s
[Task 11/25] Current/Best: 3.10/ 21.00 GFLOPS | Progress: (16/20) | 12.24 s
[Task 11/25] Current/Best: 8.85/ 23.14 GFLOPS | Progress: (20/20) | 14.52 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.59/ 15.59 GFLOPS | Progress: (4/20) | 4.45 s
[Task 12/25] Current/Best: 14.03/ 15.90 GFLOPS | Progress: (8/20) | 7.08 s
[Task 12/25] Current/Best: 9.19/ 16.97 GFLOPS | Progress: (12/20) | 10.24 s
[Task 12/25] Current/Best: 9.36/ 16.97 GFLOPS | Progress: (16/20) | 19.74 s
[Task 12/25] Current/Best: 18.38/ 18.38 GFLOPS | Progress: (20/20) | 21.79 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 7.61/ 13.55 GFLOPS | Progress: (4/20) | 5.13 s
[Task 13/25] Current/Best: 6.10/ 15.32 GFLOPS | Progress: (8/20) | 8.80 s
[Task 13/25] Current/Best: 20.78/ 20.78 GFLOPS | Progress: (12/20) | 10.80 s
[Task 13/25] Current/Best: 20.78/ 20.78 GFLOPS | Progress: (16/20) | 14.99 s
[Task 13/25] Current/Best: 18.84/ 20.78 GFLOPS | Progress: (20/20) | 18.08 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 20.89/ 20.89 GFLOPS | Progress: (4/20) | 3.94 s
[Task 14/25] Current/Best: 13.64/ 20.89 GFLOPS | Progress: (8/20) | 6.84 s
[Task 14/25] Current/Best: 8.75/ 20.89 GFLOPS | Progress: (12/20) | 8.56 s
[Task 14/25] Current/Best: 12.62/ 20.89 GFLOPS | Progress: (16/20) | 13.29 s
[Task 14/25] Current/Best: 8.98/ 20.89 GFLOPS | Progress: (20/20) | 16.52 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 9.33/ 21.14 GFLOPS | Progress: (4/20) | 5.32 s
[Task 15/25] Current/Best: 10.08/ 21.14 GFLOPS | Progress: (8/20) | 9.77 s
[Task 15/25] Current/Best: 11.05/ 21.14 GFLOPS | Progress: (12/20) | 15.06 s
[Task 15/25] Current/Best: 13.15/ 21.14 GFLOPS | Progress: (16/20) | 17.19 s
[Task 15/25] Current/Best: 6.20/ 21.14 GFLOPS | Progress: (20/20)
| 18.54 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (4/20) | 3.17 s
[Task 16/25] Current/Best: 16.78/ 20.48 GFLOPS | Progress: (8/20) | 4.82 s
[Task 16/25] Current/Best: 16.09/ 20.48 GFLOPS | Progress: (12/20) | 7.09 s
[Task 16/25] Current/Best: 21.18/ 21.18 GFLOPS | Progress: (16/20) | 8.88 s
[Task 16/25] Current/Best: 3.07/ 21.18 GFLOPS | Progress: (20/20) | 10.88 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.25/ 17.65 GFLOPS | Progress: (4/20) | 4.36 s
[Task 17/25] Current/Best: 12.54/ 20.91 GFLOPS | Progress: (8/20) | 6.59 s
[Task 17/25] Current/Best: 10.46/ 20.91 GFLOPS | Progress: (12/20) | 9.19 s
[Task 17/25] Current/Best: 10.34/ 20.91 GFLOPS | Progress: (16/20) | 11.62 s
[Task 17/25] Current/Best: 11.50/ 23.30 GFLOPS | Progress: (20/20) | 14.13 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (4/20) | 4.76 s
[Task 18/25] Current/Best: 3.08/ 19.86 GFLOPS | Progress: (8/20) | 7.71 s
[Task 18/25] Current/Best: 12.81/ 19.86 GFLOPS | Progress: (12/20) | 11.85 s
[Task 18/25] Current/Best: 10.21/ 19.86 GFLOPS | Progress: (16/20) | 17.13 s
[Task 18/25] Current/Best: 12.80/ 19.86 GFLOPS | Progress: (20/20) | 19.52 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.84/ 20.02 GFLOPS | Progress: (4/20) | 4.69 s
[Task 19/25] Current/Best: 18.27/ 20.02 GFLOPS | Progress: (8/20) | 8.65 s
[Task 19/25] Current/Best: 1.55/ 20.02 GFLOPS | Progress: (12/20) | 13.16 s
[Task 19/25] Current/Best: 10.54/ 20.02 GFLOPS | Progress: (16/20) | 17.18 s
[Task 19/25] Current/Best: 18.05/ 20.02 GFLOPS | Progress: (20/20) | 21.10 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.36/ 10.36 GFLOPS | Progress: (4/20) | 3.94 s
[Task 20/25] Current/Best: 15.43/ 16.45 GFLOPS | Progress: (8/20) | 6.05 s Done.
-
[Task 20/25] Current/Best: 14.51/ 16.45 GFLOPS | Progress: (12/20) | 8.35 s
[Task 20/25] Current/Best: 15.07/ 17.93 GFLOPS | Progress: (16/20) | 10.86 s
[Task 20/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (20/20) | 14.04 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 16.34/ 18.87 GFLOPS | Progress: (4/20) | 3.24 s
[Task 21/25] Current/Best: 14.55/ 22.14 GFLOPS | Progress: (8/20) | 5.37 s
[Task 21/25] Current/Best: 9.79/ 22.14 GFLOPS | Progress: (12/20) | 6.64 s
[Task 21/25] Current/Best: 5.25/ 22.14 GFLOPS | Progress: (16/20) | 9.65 s
[Task 21/25] Current/Best: 13.51/ 22.14 GFLOPS | Progress: (20/20) | 12.00 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 16.49/ 16.49 GFLOPS | Progress: (4/20) | 3.82 s
[Task 22/25] Current/Best: 18.93/ 18.93 GFLOPS | Progress: (8/20)
| 6.06 s
[Task 22/25] Current/Best: 16.83/ 18.93 GFLOPS | Progress: (12/20) | 7.42 s
[Task 22/25] Current/Best: 10.23/ 18.93 GFLOPS | Progress: (16/20) | 11.43 s
[Task 22/25] Current/Best: 14.06/ 20.22 GFLOPS | Progress: (20/20) | 12.89 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 18.40/ 19.48 GFLOPS | Progress: (4/20) | 9.26 s
[Task 23/25] Current/Best: 12.17/ 19.48 GFLOPS | Progress: (8/20) | 11.52 s
[Task 23/25] Current/Best: 23.51/ 23.51 GFLOPS | Progress: (12/20) | 15.78 s
[Task 23/25] Current/Best: 8.20/ 23.51 GFLOPS | Progress: (16/20) | 19.25 s
[Task 23/25] Current/Best: 13.73/ 23.51 GFLOPS | Progress: (20/20) | 27.90 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.65/ 6.65 GFLOPS | Progress: (4/20) | 12.26 s Done.
-
[Task 24/25] Current/Best: 8.10/ 8.10 GFLOPS | Progress: (8/20) | 23.57 s
[Task 24/25] Current/Best: 2.25/ 9.81 GFLOPS | Progress: (12/20) | 35.23 s
[Task 24/25] Current/Best: 2.04/ 9.81 GFLOPS | Progress: (16/20) | 45.95 s
[Task 24/25] Current/Best: 1.67/ 9.81 GFLOPS | Progress: (20/20) | 56.70 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 5.84 GFLOPS | Progress: (4/20) | 3.81 s
[Task 25/25] Current/Best: 8.98/ 8.98 GFLOPS | Progress: (8/20) | 14.49 s
[Task 25/25] Current/Best: 4.84/ 9.98 GFLOPS | Progress: (12/20) | 19.19 s
[Task 25/25] Current/Best: 1.55/ 9.98 GFLOPS | Progress: (16/20) | 24.53 s
[Task 25/25] Current/Best: 5.79/ 9.98 GFLOPS | Progress: (20/20) | 35.03 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 10.14/ 13.53 GFLOPS | Progress: (4/20) | 8.64 s
[Task 1/25] Current/Best: 5.60/ 16.35 GFLOPS | Progress: (8/20) | 11.92 s
[Task 1/25] Current/Best: 11.21/ 16.35 GFLOPS | Progress: (12/20) | 15.55 s
[Task 1/25] Current/Best: 9.67/ 22.50 GFLOPS | Progress: (16/20) | 18.67 s
[Task 1/25] Current/Best: 9.57/ 22.50 GFLOPS | Progress: (20/20) | 21.93 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.90/ 14.05 GFLOPS | Progress: (4/20) | 3.20 s
[Task 2/25] Current/Best: 9.66/ 14.05 GFLOPS | Progress: (8/20) | 6.02 s
[Task 2/25] Current/Best: 16.53/ 16.53 GFLOPS | Progress: (12/20) | 7.41 s
[Task 2/25] Current/Best: 22.14/ 22.14 GFLOPS | Progress: (16/20) | 8.71 s
[Task 2/25] Current/Best: 6.28/ 22.14 GFLOPS | Progress: (20/20) | 9.84 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 21.86/ 21.86 GFLOPS | Progress: (4/20) | 3.28 s
[Task 3/25] Current/Best: 15.81/ 21.86 GFLOPS | Progress: (8/20) | 5.42 s
[Task 3/25] Current/Best: 1.63/ 21.86 GFLOPS | Progress: (12/20) | 9.25 s
[Task 3/25] Current/Best: 22.98/ 22.98 GFLOPS | Progress: (16/20) | 11.03 s
[Task 3/25] Current/Best: 5.91/ 22.98 GFLOPS | Progress: (20/20) | 13.72 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 19.00/ 20.36 GFLOPS | Progress: (4/20) | 2.70 s
[Task 4/25] Current/Best: 16.84/ 20.36 GFLOPS | Progress: (8/20) | 4.83 s
[Task 4/25] Current/Best: 10.47/ 20.36 GFLOPS | Progress: (12/20) | 9.49 s
[Task 4/25] Current/Best: 13.86/ 20.36 GFLOPS | Progress: (16/20) | 11.45 s
[Task 4/25] Current/Best: 11.82/ 20.36 GFLOPS | Progress: (20/20) | 16.32 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.48/ 22.95 GFLOPS | Progress: (4/20) | 3.14 s
[Task 5/25] Current/Best: 15.97/ 22.95 GFLOPS | Progress: (8/20) | 5.00 s
[Task 5/25] Current/Best: 14.82/ 22.95 GFLOPS | Progress: (12/20) | 6.80 s
[Task 5/25] Current/Best: 18.56/ 22.95 GFLOPS | Progress: (16/20) | 8.58 s
[Task 5/25] Current/Best: 12.20/ 22.95 GFLOPS | Progress: (20/20) | 11.00 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.36/ 15.91 GFLOPS | Progress: (4/20) | 4.23 s
[Task 6/25] Current/Best: 12.42/ 15.91 GFLOPS | Progress: (8/20) | 6.45 s
[Task 6/25] Current/Best: 5.32/ 18.16 GFLOPS | Progress: (12/20) | 8.65 s
[Task 6/25] Current/Best: 12.41/ 22.60 GFLOPS | Progress: (16/20) | 10.73 s
[Task 6/25] Current/Best: 17.92/ 22.60 GFLOPS | Progress: (20/20) | 13.09 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.66/ 13.85 GFLOPS | Progress: (4/20) | 4.15 s
[Task 7/25] Current/Best: 13.85/ 16.04 GFLOPS | Progress: (8/20) | 6.22 s
[Task 7/25] Current/Best: 19.09/ 19.09 GFLOPS | Progress: (12/20) | 8.95 s
[Task 7/25] Current/Best: 19.41/ 19.41 GFLOPS | Progress: (16/20) | 11.20 s
[Task 7/25] Current/Best: 14.91/ 19.41 GFLOPS | Progress: (20/20) | 13.57 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.70/ 16.43 GFLOPS | Progress: (4/20) | 12.71 s
[Task 8/25] Current/Best: 4.07/ 18.01 GFLOPS | Progress: (8/20) | 15.46 s
[Task 8/25] Current/Best: 15.65/ 18.01 GFLOPS | Progress: (12/20) | 19.38 s
[Task 8/25] Current/Best: 2.57/ 18.01 GFLOPS | Progress: (16/20) | 30.29 s
[Task 8/25] Current/Best: 4.21/ 18.01 GFLOPS | Progress: (20/20) | 32.54 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.90/ 16.49 GFLOPS | Progress: (4/20) | 10.85 s
[Task 9/25] Current/Best: 13.72/ 16.49 GFLOPS | Progress: (8/20) | 16.62 s
[Task 9/25] Current/Best: 14.74/ 19.60 GFLOPS | Progress: (12/20) | 17.94 s
[Task 9/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (16/20) | 20.08 s
[Task 9/25] Current/Best: 6.85/ 20.74 GFLOPS | Progress: (2
0/20) | 22.03 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 16.20/ 16.20 GFLOPS | Progress: (4/20) | 3.80 s
[Task 10/25] Current/Best: 20.42/ 22.36 GFLOPS | Progress: (8/20) | 5.15 s
[Task 10/25] Current/Best: 16.37/ 22.36 GFLOPS | Progress: (12/20) | 7.01 s
[Task 10/25] Current/Best: 4.89/ 22.36 GFLOPS | Progress: (16/20) | 11.07 s
[Task 10/25] Current/Best: 12.72/ 22.36 GFLOPS | Progress: (20/20) | 12.44 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.83/ 19.21 GFLOPS | Progress: (4/20) | 3.57 s
[Task 11/25] Current/Best: 12.23/ 19.21 GFLOPS | Progress: (8/20) | 6.69 s
[Task 11/25] Current/Best: 12.35/ 19.37 GFLOPS | Progress: (12/20) | 8.47 s
[Task 11/25] Current/Best: 13.40/ 19.37 GFLOPS | Progress: (16/20) | 11.36 s
[Task 11/25] Current/Best: 10.70/ 21.00 GFLOPS | Progress: (20/20) | 13.90 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 6.42/ 12.52 GFLOPS | Progress: (4/20) | 3.42 s
[Task 12/25] Current/Best: 18.02/ 18.02 GFLOPS | Progress: (8/20) | 5.17 s
[Task 12/25] Current/Best: 13.29/ 18.02 GFLOPS | Progress: (12/20) | 7.86 s
[Task 12/25] Current/Best: 18.32/ 18.32 GFLOPS | Progress: (16/20) | 9.68 s
[Task 12/25] Current/Best: 14.53/ 18.32 GFLOPS | Progress: (20/20) | 15.11 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (4/20) | 5.20 s
[Task 13/25] Current/Best: 20.25/ 20.51 GFLOPS | Progress: (8/20) | 7.45 s
[Task 13/25] Current/Best: 13.38/ 20.51 GFLOPS | Progress: (12/20) | 10.63 s
[Task 13/25] Current/Best: 6.20/ 20.51 GFLOPS | Progress: (16/20) | 14.53 s
[Task 13/25] Current/Best: 9.84/ 20.67 GFLOPS | Progress: (20/20) | 16.50 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.23/ 12.30 GFLOPS | Progress: (4/20) | 4.12 s
[Task 14/25] Current/Best: 11.01/ 18.23 GFLOPS | Progress: (8/20) | 7.07 s
[Task 14/25] Current/Best: 14.90/ 18.29 GFLOPS | Progress: (12/20) | 9.34 s
[Task 14/25] Current/Best: 5.80/ 19.91 GFLOPS | Progress: (16/20) | 13.83 s
[Task 14/25] Current/Best: 1.58/ 19.91 GFLOPS | Progress: (20/20) | 17.03 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 15/25] Current/Best: 9.27/ 19.90 GFLOPS | Progress: (4/20) | 5.66 s
[Task 15/25] Current/Best: 22.80/ 22.80 GFLOPS | Progress: (8/20) | 8.06 s
[Task 15/25] Current/Best: 11.36/ 22.80 GFLOPS | Progress: (12/20) | 9.65 s
[Task 15/25] Current/Best: 23.23/ 23.23 GFLOPS | Progress: (16/20) | 13.72 s
[Task 15/25] Current/Best: 4.92/ 23.23 GFLOPS | Progress: (20/20) | 15.65 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.99/ 14.99 GFLOPS | Progress: (4/20) | 3.82 s
[Task 16/25] Current/Best: 19.17/ 22.20 GFLOPS | Progress: (8/20) | 5.35 s
[Task 16/25] Current/Best: 17.36/ 22.20 GFLOPS | Progress: (12/20) | 6.61 s
[Task 16/25] Current/Best: 2.95/ 22.20 GFLOPS | Progress: (16/20) | 8.18 s
[Task 16/25] Current/Best: 20.76/ 22.20 GFLOPS | Progress: (20/20) | 9.39 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.90/ 11.90 GFLOPS | Progress: (4/20) | 4.41 s
[Task 17/25] Current/Best: 6.14/ 11.90 GFLOPS | Progress: (8/20) | 7.16 s
[Task 17/25] Current/Best: 14.62/ 21.94 GFLOPS | Progress: (12/20) | 9.86 s
[Task 17/25] Current/Best: 15.01/ 21.94 GFLOPS | Progress: (16/20) | 11.98 s
[Task 17/25] Current/Best: 7.65/ 21.94 GFLOPS | Progress: (20/20) | 14.63 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 9.16/ 20.98 GFLOPS | Progress: (4/20) | 8.70 s
[Task 18/25] Current/Best: 18.97/ 20.98 GFLOPS | Progress: (8/20) | 10.58 s
[Task 18/25] Current/Best: 11.62/ 20.98 GFLOPS | Progress: (12/20) | 12.91 s
[Task 18/25] Current/Best: 8.24/ 20.98 GFLOPS | Progress: (16/20) | 14.76 s
[Task 18/25] Current/Best: 10.73/ 20.98 GFLOPS | Progress: (20/20) | 22.40 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 1.55/ 14.13 GFLOPS | Progress: (4/20) | 6.29 s
[Task 19/25] Current/Best: 3.08/ 17.94 GFLOPS | Progress: (8/20) | 11.09 s
[Task 19/25] Current/Best: 11.04/ 18.08 GFLOPS | Progress: (12/20) | 17.53 s
[Task 19/25] Current/Best: 13.79/ 21.18 GFLOPS | Progress: (16/20) | 19.27 s
[Task 19/25] Current/Best: 12.56/ 21.18 GFLOPS | Progress: (20/20) | 23.10 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 16.58/ 22.10 GFLOPS | Progress: (4/20) | 3.44 s
[Task 20/25] Current/Best: 20.24/ 22.10 GFLOPS | Progress: (8/20) | 5.46 s
[Task 20/25] Current/Best: 5.31/ 22.10 GFLOPS | Progress: (12/20) | 7.68 s
[Task 20/25] Current/Best: 6.34/ 22.10 GFLOPS | Progress: (16/20) | 10.61 s
[Task 20/25] Current/Best: 16.52/ 22.10 GFLOPS | Progress: (20/20) | 14.32 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 21/25] Current/Best: 11.36/ 11.36 GFLOPS | Progress: (4/20) | 4.67 s
[Task 21/25] Current/Best: 9.45/ 21.12 GFLOPS | Progress: (8/20) | 7.62 s
[Task 21/25] Current/Best: 14.25/ 21.12 GFLOPS | Progress: (12/20) | 8.82 s
[Task 21/25] Current/Best: 12.57/ 21.12 GFLOPS | Progress: (16/20) | 11.01 s
[Task 21/25] Current/Best: 2.73/ 21.12 GFLOPS | Progress: (20/20) | 15.67 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.17/ 19.80 GFLOPS | Progress: (4/20) | 4.05 s
[Task 22/25] Current/Best: 9.14/ 19.80 GFLOPS | Progress: (8/20) | 6.05 s
[Task 22/25] Current/Best: 10.73/ 19.80 GFLOPS | Progress: (12/20) | 8.18 s
[Task 22/25] Current/Best: 9.58/ 19.80 GFLOPS | Progress: (16/20) | 10.79 s
[Task 22/25] Current/Best: 4.47/ 19.80 GFLOPS | Progress: (20/20) | 12.41 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 5.34/ 18.29 GFLOPS | Progress: (4/20) | 4.52 s
[Task 23/25] Current/Best: 23.03/ 23.03 GFLOPS | Progress: (8/20) | 6.77 s
[Task 23/25] Current/Best: 9.30/ 23.03 GFLOPS | Progress: (12/20) | 9.43 s
[Task 23/25] Current/Best: 9.27/ 23.03 GFLOPS | Progress: (16/20) | 11.91 s
[Task 23/25] Current/Best: 21.84/ 23.03 GFLOPS | Progress: (20/20) | 13.70 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 10.10/ 10.10 GFLOPS | Progress: (4/20) | 3.10 s
[Task 24/25] Current/Best: 2.66/ 10.10 GFLOPS | Progress: (8/20) | 13.78 s
[Task 24/25] Current/Best: 3.25/ 10.10 GFLOPS | Progress: (12/20) | 25.36 s
[Task 24/25] Current/Best: 10.30/ 10.30 GFLOPS | Progress: (16/20) | 36.02 s
[Task 24/25] Current/Best: 2.89/ 10.30 GFLOPS | Progress: (20/20) | 47.68 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 2.87/ 7.32 GFLOPS | Progress: (4/20) | 6.49 s
[Task 25/25] Current/Best: 3.46/ 7.32 GFLOPS | Progress: (8/20) | 17.24 s
[Task 25/25] Current/Best: 3.50/ 7.32 GFLOPS | Progress: (12/20) | 28.76 s
[Task 25/25] Current/Best: 1.54/ 8.88 GFLOPS | Progress: (16/20) | 40.47 s
[Task 25/25] Current/Best: 3.46/ 8.88 GFLOPS | Progress: (20/20) | 43.57 s
@@ -730,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 412.58942520000346, 'median': 412.4597152500087, 'std': 0.9612452629635656}
- unoptimized: {'mean': 516.7291401700004, 'median': 517.3745978499994, 'std': 2.3085657145066754}
+ optimized: {'mean': 399.857247559994, 'median': 399.1185426499669, 'std': 2.4755024021350205}
+ unoptimized: {'mean': 513.475046199992, 'median': 514.1611493499568, 'std': 3.162537198510625}
@@ -754,7 +755,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 10.417 seconds)
+ **Total running time of the script:** ( 11 minutes 7.753 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 8ce8a7a52c..7cee35c1a2 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
- 1.224e-07 secs/op
+ 1.27e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 763878791a..f319466e0b 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, 0x983a130)), stage(b, placeholder(b, 0x7de9160)), 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, 0x21d7bff0)), stage(b, placeholder(b, 0x10797ad0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index cde70c8b8f..7cf11a4c28 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
=================
-**14:34.250** total execution time for **tutorial** files:
+**14:40.344** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:10.417 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:07.753 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:22.689 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:34.822 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.805 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.767 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.015 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.325 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:21.339 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.911 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.047 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.814 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.769 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.765 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.160 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.179 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 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_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index e63d33f776..284c3cabf5 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000010
+ parallel: 0.000006
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.396420000986836e-06 1.0
- naive 6.7525e-06 0.9129416662519267
- parallel 9.514699999999999e-06 1.2863926059810746
- vector 2.46147e-05 3.3279208044859385
+ numpy 7.130609992600511e-06 1.0
+ naive 6.6974e-06 0.9392464329068541
+ parallel 6.0754e-06 0.8520168690062266
+ vector 2.4708899999999996e-05 3.4651874139296095
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018807
+ Numpy running time: 0.018014
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.476480
+ none: 3.399562
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.298771
+ blocking: 0.291581
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.328130
+ vectorization: 0.331726
@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: 0.118521
+ loop permutation: 0.118926
@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: 0.110055
+ array packing: 0.109656
@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: 0.111067
+ block caching: 0.111001
@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: 0.147176
+ parallelization: 0.146087
@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 3.47647962 1.0
- blocking 0.2987710289 0.08594068182686485
- vectorization 0.32813003890000003 0.09438572198504648
- loop permutation 0.11852084510000001 0.03409220189819494
- array packing 0.1100552638 0.03165710023635922
- block caching 0.11106684689999999 0.03194807939072572
- parallelization 0.1471763221 0.04233487268364887
+ none 3.3995616925 1.0
+ blocking 0.2915809708 0.08577016603148467
+ vectorization 0.3317258383 0.09757900232604766
+ loop permutation 0.11892609970000001 0.034982774385995355
+ array packing 0.10965607720000001 0.03225594565379402
+ block caching 0.1110012953 0.03265164904784266
+ parallelization 0.1460874748 0.04297244410133617
@@ -1663,7 +1663,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.805 seconds)
+ **Total running time of the script:** ( 1 minutes 0.767 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 960f12d9ff..f8651f7c50 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-750ba9f742da772e730b9d77075834dd53e37682
+16bb1a6c2ee7a8f68f15ab8710588c75880e0dd5
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index cd07d7c20a..55ecaebf62 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 9.296 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.050 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 f6f01a4639..ba765a2ae8 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 954ms/step
+1/1 [==============================] - 1s 970ms/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 91b1686e72..b12158bdc7 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.zip7e9e7920-d32c-45ff-980e-29907c60a058 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.zipc644c5f8-48a3-4006-93ef-e033773d2bad 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 563d498542..a50871c038 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,10 +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]
- 32%|###1 | 13.2M/41.5M [00:00<00:00, 132MB/s]
- 62%|######2 | 25.8M/41.5M [00:00<00:00, 87.5MB/s]
- 84%|########4 | 34.9M/41.5M [00:00<00:00, 55.6MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 69.2MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 61.1MB/s]
+ 38%|###7 | 15.6M/41.5M [00:00<00:00, 70.8MB/s]
+ 54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.2MB/s]
+ 69%|######8 | 28.6M/41.5M [00:00<00:00, 54.0MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00<00:00, 42.6MB/s]
+ 93%|#########2| 38.5M/41.5M [00:00<00:00, 43.0MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 47.6MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index fb3dcaa6d0..a726873fd9 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 27%|##7 | 12.3M/44.7M [00:00<00:00, 129MB/s]
- 55%|#####4 | 24.6M/44.7M [00:00<00:00, 109MB/s]
- 79%|#######8 | 35.1M/44.7M [00:00<00:00, 106MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
+ 23%|##2 | 10.1M/44.7M [00:00<00:00, 53.6MB/s]
+ 54%|#####3 | 24.0M/44.7M [00:00<00:00, 87.2MB/s]
+ 74%|#######4 | 33.2M/44.7M [00:00<00:00, 64.1MB/s]
+ 99%|#########8| 44.2M/44.7M [00:00<00:00, 67.5MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 68.4MB/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 7930a741f8..1b63fd04bb 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 11.488 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.507 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 52bdd44cbd..2e40e2c765 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">ΒΆ</a></h1>
-<p><strong>05:46.583</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:50.997</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -348,44 +348,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:11.488</p></td>
+<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>01:12.050</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:09.296</p></td>
+<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>01:11.507</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>00:46.777</p></td>
+<td><p>00:47.114</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>00:32.571</p></td>
+<td><p>00:33.579</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:30.630</p></td>
+<td><p>00:30.285</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>00:27.261</p></td>
+<td><p>00:26.691</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>00:24.739</p></td>
+<td><p>00:25.748</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.956</p></td>
+<td><p>00:23.020</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>00:18.499</p></td>
+<td><p>00:18.618</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>00:02.366</p></td>
+<td><p>00:02.386</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 e64fa129bb..0468acac2d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2452 16.2177 17.0322 15.6039 0.4963
+ 16.3597 16.4060 16.8215 15.7883 0.4284
</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 69cd76ad2e..d932a25a15 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,23 +453,27 @@ 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]
- 8%|7 | 13.5M/170M [00:00<00:01, 141MB/s]
- 16%|#5 | 27.0M/170M [00:00<00:01, 113MB/s]
- 22%|##2 | 38.1M/170M [00:00<00:01, 107MB/s]
- 29%|##8 | 48.5M/170M [00:00<00:01, 102MB/s]
- 35%|###4 | 58.7M/170M [00:00<00:01, 104MB/s]
- 40%|#### | 68.7M/170M [00:00<00:01, 103MB/s]
- 46%|####6 | 78.5M/170M [00:00<00:00, 102MB/s]
- 52%|#####1 | 88.3M/170M [00:00<00:00, 101MB/s]
- 58%|#####7 | 98.0M/170M [00:00<00:00, 101MB/s]
- 63%|######3 | 108M/170M [00:01<00:00, 100MB/s]
- 69%|######9 | 117M/170M [00:01<00:00, 101MB/s]
- 75%|#######4 | 127M/170M [00:01<00:00, 101MB/s]
- 80%|######## | 137M/170M [00:01<00:00, 99.4MB/s]
- 86%|########6 | 146M/170M [00:01<00:00, 101MB/s]
- 92%|#########1| 156M/170M [00:01<00:00, 101MB/s]
- 98%|#########7| 166M/170M [00:01<00:00, 100MB/s]
-100%|##########| 170M/170M [00:01<00:00, 102MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:03, 47.6MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:03, 53.7MB/s]
+ 12%|#1 | 19.6M/170M [00:00<00:03, 42.8MB/s]
+ 15%|#5 | 26.1M/170M [00:00<00:03, 49.7MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:03, 46.3MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:02, 50.8MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:02, 56.3MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:01, 73.7MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 70.4MB/s]
+ 48%|####8 | 82.1M/170M [00:01<00:01, 74.2MB/s]
+ 52%|#####2 | 89.1M/170M [00:01<00:01, 71.3MB/s]
+ 57%|#####6 | 96.0M/170M [00:01<00:01, 70.3MB/s]
+ 60%|###### | 103M/170M [00:01<00:01, 68.3MB/s]
+ 64%|######4 | 109M/170M [00:01<00:00, 63.9MB/s]
+ 71%|####### | 120M/170M [00:01<00:00, 69.7MB/s]
+ 79%|#######8 | 134M/170M [00:02<00:00, 88.9MB/s]
+ 84%|########3 | 143M/170M [00:02<00:00, 84.5MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 76.5MB/s]
+ 94%|#########4| 160M/170M [00:02<00:00, 69.6MB/s]
+ 99%|#########8| 168M/170M [00:02<00:00, 68.6MB/s]
+100%|##########| 170M/170M [00:02<00:00, 67.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -567,7 +571,7 @@ 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 15.840 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 12.732 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 5230b13c63..b0ada9e8ae 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]
- 60%|#####9 | 8.12M/13.6M [00:00<00:00, 77.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 108MB/s]
+ 63%|######3 | 8.59M/13.6M [00:00<00:00, 90.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 104MB/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)
- 90.5757 90.4862 93.7646 90.3663 0.3669
+ 90.4625 90.3304 92.9230 90.1025 0.4444
</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">ΒΆ</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.376 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.933 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 820aa2150d..8fa9dbaa1d 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)
- 119.7653 119.6711 124.5059 118.6998 0.7190
+ 120.3298 120.2409 125.2988 119.4781 0.5993
</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 33.832 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 31.670 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 c429602f76..88deeaa139 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 17.550 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.444 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 907bee9f1e..d728970d99 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,22 +462,25 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|5 | 6777/132723 [00:00<00:01, 67761.66KB/s]
- 12%|#1 | 15316/132723 [00:00<00:01, 78127.72KB/s]
- 18%|#8 | 23934/132723 [00:00<00:01, 81799.25KB/s]
- 25%|##4 | 32571/132723 [00:00<00:01, 83601.05KB/s]
- 31%|###1 | 41226/132723 [00:00<00:01, 84662.24KB/s]
- 37%|###7 | 49768/132723 [00:00<00:00, 84916.11KB/s]
- 44%|####4 | 58425/132723 [00:00<00:00, 85449.00KB/s]
- 51%|##### | 67096/132723 [00:00<00:00, 85847.30KB/s]
- 57%|#####7 | 75849/132723 [00:00<00:00, 86369.70KB/s]
- 64%|######3 | 84513/132723 [00:01<00:00, 86451.83KB/s]
- 70%|####### | 93217/132723 [00:01<00:00, 86627.49KB/s]
- 77%|#######6 | 101880/132723 [00:01<00:00, 85832.19KB/s]
- 83%|########3 | 110652/132723 [00:01<00:00, 86397.41KB/s]
- 90%|########9 | 119345/132723 [00:01<00:00, 86555.09KB/s]
- 97%|#########6| 128084/132723 [00:01<00:00, 86803.61KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 85154.65KB/s]
+ 4%|3 | 4964/132723 [00:00<00:02, 49635.79KB/s]
+ 9%|9 | 12094/132723 [00:00<00:01, 62376.41KB/s]
+ 14%|#4 | 19228/132723 [00:00<00:01, 66466.48KB/s]
+ 20%|#9 | 26375/132723 [00:00<00:01, 68405.82KB/s]
+ 25%|##5 | 33777/132723 [00:00<00:01, 70425.07KB/s]
+ 31%|###1 | 41149/132723 [00:00<00:01, 71538.68KB/s]
+ 37%|###6 | 48577/132723 [00:00<00:01, 72431.01KB/s]
+ 42%|####2 | 56039/132723 [00:00<00:01, 73122.32KB/s]
+ 48%|####7 | 63567/132723 [00:00<00:00, 73795.36KB/s]
+ 53%|#####3 | 71000/132723 [00:01<00:00, 73957.47KB/s]
+ 59%|#####9 | 78512/132723 [00:01<00:00, 74310.80KB/s]
+ 65%|######4 | 86209/132723 [00:01<00:00, 75116.42KB/s]
+ 71%|####### | 93721/132723 [00:01<00:00, 71919.47KB/s]
+ 76%|#######6 | 101155/132723 [00:01<00:00, 72626.41KB/s]
+ 82%|########1 | 108823/132723 [00:01<00:00, 73820.89KB/s]
+ 88%|########7 | 116479/132723 [00:01<00:00, 74631.02KB/s]
+ 94%|#########3| 124138/132723 [00:01<00:00, 75212.02KB/s]
+100%|#########9| 132158/132723 [00:01<00:00, 76696.21KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 72772.46KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -516,7 +519,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.662 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 0.093 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 1d5563bbdf..0854b4be6e 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">ΒΆ</a></h1>
-<p><strong>12:42.323</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:43.530</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:15.840</p></td>
+<td><p>03:12.732</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>03:02.662</p></td>
+<td><p>03:00.093</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>02:33.832</p></td>
+<td><p>02:31.670</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>01:17.550</p></td>
+<td><p>01:26.444</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>01:05.376</p></td>
+<td><p>01:05.933</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>00:35.823</p></td>
+<td><p>00:35.850</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>00:25.649</p></td>
+<td><p>00:25.631</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>00:25.586</p></td>
+<td><p>00:25.172</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>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 90fc9f130c..f64bdfa094 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.zip5e9b1990-ef6d-4452-89f7-cb1e62dc2570 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.zipddcd3805-d4ac-4f71-ac80-741cf80ee93b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>Itβs 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 0cad513ce5..3b9d175a00 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">ΒΆ</a></h1>
-<p><strong>00:47.105</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.584</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:43.664</p></td>
+<td><p>00:43.245</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>00:02.401</p></td>
+<td><p>00:02.323</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>00:01.033</p></td>
+<td><p>00:01.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 600264b2a6..05a9e5538e 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: 6732us [6732us] (45.93%; 45.93%)
-FoldScaleAxis: 7924us [6us] (54.07%; 54.07%)
- FoldConstant: 7918us [1633us] (54.03%; 99.93%)
- InferType: 6285us [6285us] (42.88%; 79.37%)
+InferType: 6612us [6612us] (46.52%; 46.52%)
+FoldScaleAxis: 7600us [5us] (53.48%; 53.48%)
+ FoldConstant: 7595us [1522us] (53.44%; 99.93%)
+ InferType: 6073us [6073us] (42.73%; 79.96%)
</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: 6355us [6355us] (44.45%; 44.45%)
-FoldScaleAxis: 7942us [5us] (55.55%; 55.55%)
- FoldConstant: 7938us [1631us] (55.52%; 99.94%)
- InferType: 6306us [6306us] (44.11%; 79.45%)
+InferType: 6154us [6154us] (44.83%; 44.83%)
+FoldScaleAxis: 7573us [5us] (55.17%; 55.17%)
+ FoldConstant: 7568us [1526us] (55.13%; 99.94%)
+ InferType: 6042us [6042us] (44.02%; 79.84%)
</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 c5faaa7a33..8501e9324f 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: 44.954753 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 52.604576 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 b1b546f803..434f365252 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: 10.586887 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.859827 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 1807aab8b3..516e77477b 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: 0.018589
-Baseline: 3.342600
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018560
+Baseline: 3.432973
</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: 0.298713
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301429
</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: 0.337551
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336746
</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: 0.115560
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116359
</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: 0.109716
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109505
</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: 0.111788
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112132
</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: 0.147106
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146623
</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 22fd9e35ca..bd07b8a878 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">ΒΆ</a></h1>
-<p><strong>00:34.573</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.985</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.130</p></td>
+<td><p>00:32.377</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>00:01.374</p></td>
+<td><p>00:01.471</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>00:01.069</p></td>
+<td><p>00:01.137</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 a3ec4efc4b..734851bad1 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">ΒΆ</a></h1>
-<p><strong>08:58.752</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:16.563</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>05:33.283</p></td>
+<td><p>05:46.350</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>01:32.024</p></td>
+<td><p>01:32.897</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>01:03.131</p></td>
+<td><p>01:03.856</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>00:27.524</p></td>
+<td><p>00:30.392</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>00:11.791</p></td>
+<td><p>00:12.019</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>00:10.999</p></td>
+<td><p>00:11.048</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 1b6a54237c..9b748e4698 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
@@ -504,483 +504,1021 @@ 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;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [432]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[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[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
- }
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [432], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 5), 27)) && (floormod((threadIdx.x_1 + 5), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 10), 27)) && (floormod((threadIdx.x_1 + 10), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 5), 9)) && (floormod((threadIdx.x_1 + 15), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 20), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 25), 27)) && (floormod((threadIdx.x_1 + 25), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 1), 9)) && (floormod((threadIdx.x_1 + 3), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 1), 9)*7)) + floormod(blockIdx.x, 7)) + floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 8), 27)) && (floormod((threadIdx.x_1 + 8), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 256)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 13), 27)) && (floormod((threadIdx.x_1 + 13), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 256), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 13), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 288)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 6), 9)) && (floormod((threadIdx.x_1 + 18), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 288), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 6), 9)*7)) + floormod(blockIdx.x, 7)) + floormo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 320)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 23), 27)) && (floormod((threadIdx.x_1 + 23), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 320), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 352)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 1), 27)) && (floormod((threadIdx.x_1 + 1), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 352), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 384)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 2), 9)) && (floormod((threadIdx.x_1 + 6), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 384), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 2), 9)*7)) + floormod(blockIdx.x, 7)) + floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 416)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 416), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 32), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 64), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 96)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 192), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 320), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 384), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 480), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 512), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 608), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 704), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 768), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 832), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 928), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 960), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 992), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1024), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1056), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1184), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1216), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1248), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1376), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1504), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1536), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1600), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1632), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1664), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1696), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1760), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1824), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1856), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1888), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1920), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1984), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2048), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2112), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2208), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2272), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2336), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2368), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2400), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2432), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2496), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2528), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2656), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2720), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2784), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2816), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2848), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2944), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2976), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3008), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3040), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3072), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3104), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3200), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3264), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3328), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3488), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3520), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3552), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3648), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3680), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3712), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3776), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3840), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3872), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3936), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4000), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4096), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4128), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4192), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4224), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4384), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4416), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4512), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ for (rc.outer.inner: int32, 0, 2) {
+ let cse_var_171: int32 = (rc.outer.inner*216)
+ let cse_var_170: int32 = (cse_var_171 + 99)
+ let cse_var_169: int32 = (cse_var_171 + 98)
+ let cse_var_168: int32 = (cse_var_171 + 97)
+ let cse_var_167: int32 = (cse_var_171 + 96)
+ let cse_var_166: int32 = (cse_var_171 + 95)
+ let cse_var_165: int32 = (cse_var_171 + 94)
+ let cse_var_164: int32 = (cse_var_171 + 93)
+ let cse_var_163: int32 = (cse_var_171 + 92)
+ let cse_var_162: int32 = (cse_var_171 + 91)
+ let cse_var_161: int32 = (cse_var_171 + 90)
+ let cse_var_160: int32 = (cse_var_171 + 9)
+ let cse_var_159: int32 = (cse_var_171 + 89)
+ let cse_var_158: int32 = (cse_var_171 + 88)
+ let cse_var_157: int32 = (cse_var_171 + 87)
+ let cse_var_156: int32 = (cse_var_171 + 86)
+ let cse_var_155: int32 = (cse_var_171 + 85)
+ let cse_var_154: int32 = (cse_var_171 + 84)
+ let cse_var_153: int32 = (cse_var_171 + 8)
+ let cse_var_152: int32 = (cse_var_171 + 77)
+ let cse_var_151: int32 = (cse_var_171 + 76)
+ let cse_var_150: int32 = (cse_var_171 + 75)
+ let cse_var_149: int32 = (cse_var_171 + 74)
+ let cse_var_148: int32 = (cse_var_171 + 73)
+ let cse_var_147: int32 = (cse_var_171 + 72)
+ let cse_var_146: int32 = (cse_var_171 + 71)
+ let cse_var_145: int32 = (cse_var_171 + 70)
+ let cse_var_144: int32 = (cse_var_171 + 7)
+ let cse_var_143: int32 = (cse_var_171 + 69)
+ let cse_var_142: int32 = (cse_var_171 + 68)
+ let cse_var_141: int32 = (cse_var_171 + 67)
+ let cse_var_140: int32 = (cse_var_171 + 66)
+ let cse_var_139: int32 = (cse_var_171 + 65)
+ let cse_var_138: int32 = (cse_var_171 + 64)
+ let cse_var_137: int32 = (cse_var_171 + 63)
+ let cse_var_136: int32 = (cse_var_171 + 62)
+ let cse_var_135: int32 = (cse_var_171 + 61)
+ let cse_var_134: int32 = (cse_var_171 + 60)
+ let cse_var_133: int32 = (cse_var_171 + 6)
+ let cse_var_132: int32 = (cse_var_171 + 59)
+ let cse_var_131: int32 = (cse_var_171 + 58)
+ let cse_var_130: int32 = (cse_var_171 + 57)
+ let cse_var_129: int32 = (cse_var_171 + 50)
+ let cse_var_128: int32 = (cse_var_171 + 5)
+ let cse_var_127: int32 = (cse_var_171 + 49)
+ let cse_var_126: int32 = (cse_var_171 + 48)
+ let cse_var_125: int32 = (cse_var_171 + 47)
+ let cse_var_124: int32 = (cse_var_171 + 46)
+ let cse_var_123: int32 = (cse_var_171 + 45)
+ let cse_var_122: int32 = (cse_var_171 + 44)
+ let cse_var_121: int32 = (cse_var_171 + 43)
+ let cse_var_120: int32 = (cse_var_171 + 42)
+ let cse_var_119: int32 = (cse_var_171 + 41)
+ let cse_var_118: int32 = (cse_var_171 + 40)
+ let cse_var_117: int32 = (cse_var_171 + 4)
+ let cse_var_116: int32 = (cse_var_171 + 39)
+ let cse_var_115: int32 = (cse_var_171 + 38)
+ let cse_var_114: int32 = (cse_var_171 + 37)
+ let cse_var_113: int32 = (cse_var_171 + 36)
+ let cse_var_112: int32 = (cse_var_171 + 35)
+ let cse_var_111: int32 = (cse_var_171 + 34)
+ let cse_var_110: int32 = (cse_var_171 + 33)
+ let cse_var_109: int32 = (cse_var_171 + 32)
+ let cse_var_108: int32 = (cse_var_171 + 31)
+ let cse_var_107: int32 = (cse_var_171 + 30)
+ let cse_var_106: int32 = (cse_var_171 + 3)
+ let cse_var_105: int32 = (cse_var_171 + 23)
+ let cse_var_104: int32 = (cse_var_171 + 22)
+ let cse_var_103: int32 = (cse_var_171 + 212)
+ let cse_var_102: int32 = (cse_var_171 + 211)
+ let cse_var_101: int32 = (cse_var_171 + 210)
+ let cse_var_100: int32 = (cse_var_171 + 21)
+ let cse_var_99: int32 = (cse_var_171 + 209)
+ let cse_var_98: int32 = (cse_var_171 + 208)
+ let cse_var_97: int32 = (cse_var_171 + 207)
+ let cse_var_96: int32 = (cse_var_171 + 206)
+ let cse_var_95: int32 = (cse_var_171 + 205)
+ let cse_var_94: int32 = (cse_var_171 + 204)
+ let cse_var_93: int32 = (cse_var_171 + 203)
+ let cse_var_92: int32 = (cse_var_171 + 202)
+ let cse_var_91: int32 = (cse_var_171 + 201)
+ let cse_var_90: int32 = (cse_var_171 + 200)
+ let cse_var_89: int32 = (cse_var_171 + 20)
+ let cse_var_88: int32 = (cse_var_171 + 199)
+ let cse_var_87: int32 = (cse_var_171 + 198)
+ let cse_var_86: int32 = (cse_var_171 + 197)
+ let cse_var_85: int32 = (cse_var_171 + 196)
+ let cse_var_84: int32 = (cse_var_171 + 195)
+ let cse_var_83: int32 = (cse_var_171 + 194)
+ let cse_var_82: int32 = (cse_var_171 + 193)
+ let cse_var_81: int32 = (cse_var_171 + 192)
+ let cse_var_80: int32 = (cse_var_171 + 19)
+ let cse_var_79: int32 = (cse_var_171 + 185)
+ let cse_var_78: int32 = (cse_var_171 + 184)
+ let cse_var_77: int32 = (cse_var_171 + 183)
+ let cse_var_76: int32 = (cse_var_171 + 182)
+ let cse_var_75: int32 = (cse_var_171 + 181)
+ let cse_var_74: int32 = (cse_var_171 + 180)
+ let cse_var_73: int32 = (cse_var_171 + 18)
+ let cse_var_72: int32 = (cse_var_171 + 179)
+ let cse_var_71: int32 = (cse_var_171 + 178)
+ let cse_var_70: int32 = (cse_var_171 + 177)
+ let cse_var_69: int32 = (cse_var_171 + 176)
+ let cse_var_68: int32 = (cse_var_171 + 175)
+ let cse_var_67: int32 = (cse_var_171 + 174)
+ let cse_var_66: int32 = (cse_var_171 + 173)
+ let cse_var_65: int32 = (cse_var_171 + 172)
+ let cse_var_64: int32 = (cse_var_171 + 171)
+ let cse_var_63: int32 = (cse_var_171 + 170)
+ let cse_var_62: int32 = (cse_var_171 + 17)
+ let cse_var_61: int32 = (cse_var_171 + 169)
+ let cse_var_60: int32 = (cse_var_171 + 168)
+ let cse_var_59: int32 = (cse_var_171 + 167)
+ let cse_var_58: int32 = (cse_var_171 + 166)
+ let cse_var_57: int32 = (cse_var_171 + 165)
+ let cse_var_56: int32 = (cse_var_171 + 16)
+ let cse_var_55: int32 = (cse_var_171 + 158)
+ let cse_var_54: int32 = (cse_var_171 + 157)
+ let cse_var_53: int32 = (cse_var_171 + 156)
+ let cse_var_52: int32 = (cse_var_171 + 155)
+ let cse_var_51: int32 = (cse_var_171 + 154)
+ let cse_var_50: int32 = (cse_var_171 + 153)
+ let cse_var_49: int32 = (cse_var_171 + 152)
+ let cse_var_48: int32 = (cse_var_171 + 151)
+ let cse_var_47: int32 = (cse_var_171 + 150)
+ let cse_var_46: int32 = (cse_var_171 + 15)
+ let cse_var_45: int32 = (cse_var_171 + 149)
+ let cse_var_44: int32 = (cse_var_171 + 148)
+ let cse_var_43: int32 = (cse_var_171 + 147)
+ let cse_var_42: int32 = (cse_var_171 + 146)
+ let cse_var_41: int32 = (cse_var_171 + 145)
+ let cse_var_40: int32 = (cse_var_171 + 144)
+ let cse_var_39: int32 = (cse_var_171 + 143)
+ let cse_var_38: int32 = (cse_var_171 + 142)
+ let cse_var_37: int32 = (cse_var_171 + 141)
+ let cse_var_36: int32 = (cse_var_171 + 140)
+ let cse_var_35: int32 = (cse_var_171 + 14)
+ let cse_var_34: int32 = (cse_var_171 + 139)
+ let cse_var_33: int32 = (cse_var_171 + 138)
+ let cse_var_32: int32 = (cse_var_171 + 131)
+ let cse_var_31: int32 = (cse_var_171 + 130)
+ let cse_var_30: int32 = (cse_var_171 + 13)
+ let cse_var_29: int32 = (cse_var_171 + 129)
+ let cse_var_28: int32 = (cse_var_171 + 128)
+ let cse_var_27: int32 = (cse_var_171 + 127)
+ let cse_var_26: int32 = (cse_var_171 + 126)
+ let cse_var_25: int32 = (cse_var_171 + 125)
+ let cse_var_24: int32 = (cse_var_171 + 124)
+ let cse_var_23: int32 = (cse_var_171 + 123)
+ let cse_var_22: int32 = (cse_var_171 + 122)
+ let cse_var_21: int32 = (cse_var_171 + 121)
+ let cse_var_20: int32 = (cse_var_171 + 120)
+ let cse_var_19: int32 = (cse_var_171 + 12)
+ let cse_var_18: int32 = (cse_var_171 + 119)
+ let cse_var_17: int32 = (cse_var_171 + 118)
+ let cse_var_16: int32 = (cse_var_171 + 117)
+ let cse_var_15: int32 = (cse_var_171 + 116)
+ let cse_var_14: int32 = (cse_var_171 + 115)
+ let cse_var_13: int32 = (cse_var_171 + 114)
+ let cse_var_12: int32 = (cse_var_171 + 113)
+ let cse_var_11: int32 = (cse_var_171 + 112)
+ let cse_var_10: int32 = (cse_var_171 + 111)
+ let cse_var_9: int32 = (cse_var_171 + 11)
+ let cse_var_8: int32 = (cse_var_171 + 104)
+ let cse_var_7: int32 = (cse_var_171 + 103)
+ let cse_var_6: int32 = (cse_var_171 + 102)
+ let cse_var_5: int32 = (cse_var_171 + 101)
+ let cse_var_4: int32 = (cse_var_171 + 100)
+ let cse_var_3: int32 = (cse_var_171 + 10)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_171]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 1)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 2)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 27)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 28)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 29)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 54)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 55)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 56)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 81)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 82)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 83)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 108)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 109)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 110)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 135)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 136)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 137)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 162)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 163)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 164)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 189)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 190)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(cse_var_171 + 191)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_117]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_128]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_130]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_131]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_132]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_154]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_155]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_156]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_133]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_144]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_153]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_111]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_112]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_134]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_135]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_136]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_157]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_158]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_159]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_160]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_113]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_114]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_115]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_137]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_138]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_139]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_161]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_162]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_163]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_116]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_118]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_119]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_140]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_141]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_142]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_164]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_165]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_166]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_120]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_121]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_122]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_143]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_145]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_146]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_167]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_168]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_169]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[((threadIdx.x*144) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_123]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_124]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_125]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_147]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_148]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_149]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_170]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_117]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_128]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_130]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_131]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_132]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_154]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_155]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_156]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_133]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_144]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_153]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_111]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_112]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_134]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_135]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_136]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_157]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_158]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_159]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_160]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_113]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_114]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_115]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_137]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_138]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_139]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_161]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_162]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_163]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_116]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_118]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_119]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_140]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_141]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_142]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_164]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_165]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_166]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_120]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_121]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_122]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_143]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_145]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_146]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_167]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_168]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_169]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_123]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_124]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_125]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_147]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_148]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_149]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_170]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_126]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_127]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_129]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_150]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_151]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_152]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_133]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_144]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_153]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_111]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_112]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_134]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_135]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_136]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_157]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_158]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_159]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_160]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_113]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_114]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_115]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_137]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_138]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_139]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_161]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_162]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_163]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_116]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_118]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_119]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_140]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_141]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_142]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_164]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_165]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_166]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_120]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_121]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_122]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_143]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_145]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_146]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_167]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_168]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_169]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_123]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_124]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_125]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_147]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_148]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_149]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_170]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_126]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_127]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_129]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_150]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_151]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_152]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 24)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 25)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 26)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 51)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 52)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 53)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 78)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 79)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 80)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 105)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 106)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 107)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 132)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 133)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 134)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 159)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 160)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 161)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 186)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 187)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 188)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 213)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 214)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_171 + 215)]*kernel.shared_1[(((threadIdx.x*144) + (rc.outer.inner*72)) + 71)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 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[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
}
}
}
@@ -1017,7 +1555,7 @@ 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: 0.360 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.266 ms
</pre></div>
</div>
</div>
@@ -1047,34 +1585,34 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
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_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=32)
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_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=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
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_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=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
@@ -1095,12 +1633,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=32)
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=32)
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)
@@ -1120,10 +1658,10 @@ 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) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[432];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1131,420 +1669,679 @@ extern "C" __global__ void __launch_bounds__(64) default_function_kern
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[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((3 <= ((((int)threadIdx.x) + 5) % 27)) && (((((int)threadIdx.x) + 5) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % [...]
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((3 <= ((((int)threadIdx.x) + 10) % 27)) && (((((int)threadIdx.x) + 10) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (((((int)threadIdx.x) / 3) + 5) % 9)) && (((((int)threadIdx.x) + 15) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 5) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((3 <= ((((int)threadIdx.x) + 25) % 27)) && (((((int)threadIdx.x) + 25) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (((((int)threadIdx.x) / 3) + 1) % 9)) && (((((int)threadIdx.x) + 3) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 1) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : [...]
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((3 <= ((((int)threadIdx.x) + 8) % 27)) && (((((int)threadIdx.x) + 8) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 27) * 49)) + ((((((int)threadIdx.x) + 8) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 256)] = (((((3 <= ((((int)threadIdx.x) + 13) % 27)) && (((((int)threadIdx.x) + 13) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 256) / 27) * 49)) + ((((((int)threadIdx.x) + 13) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 288)] = (((((1 <= (((((int)threadIdx.x) / 3) + 6) % 9)) && (((((int)threadIdx.x) + 18) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 288) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 6) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : [...]
+ pad_temp_shared[(((int)threadIdx.x) + 320)] = (((((3 <= ((((int)threadIdx.x) + 23) % 27)) && (((((int)threadIdx.x) + 23) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 320) / 27) * 49)) + ((((((int)threadIdx.x) + 23) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 352)] = (((((3 <= ((((int)threadIdx.x) + 1) % 27)) && (((((int)threadIdx.x) + 1) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 352) / 27) * 49)) + ((((((int)threadIdx.x) + 1) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 384)] = (((((1 <= (((((int)threadIdx.x) / 3) + 2) % 9)) && (((((int)threadIdx.x) + 6) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 384) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : [...]
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 416)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 416) / 27) * 49)) + (((((int)threadIdx.x) + 11) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
}
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1216) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1312) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1376) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1408) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1504) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1600) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1632) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1664) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1696) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1760) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1888) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1984) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2048) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2208) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2272) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2336) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2368) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2432) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2528) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2560) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2656) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2816) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2848) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2944) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2976) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3008) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3040) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3072) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3104) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3200) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3264) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3328) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3392) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3424) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3488) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3520) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3552) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3648) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3680) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3712) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3776) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3872) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3936) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4000) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4096) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4160) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4192) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4288) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4384) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4576) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ __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 * 216)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 1)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 2)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 27)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 28)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 29)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 54)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 55)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 56)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 81)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 82)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 83)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 108)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 109)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 110)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 135)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 136)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 137)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 162)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 163)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 164)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 189)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 190)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 191)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 3)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 4)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 5)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 30)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 31)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 32)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 57)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 58)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 59)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 84)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 85)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 86)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 111)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 112)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 113)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 138)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 139)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 140)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 165)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 166)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 167)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 192)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 193)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 194)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 6)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 7)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 8)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 33)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 34)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 35)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 60)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 61)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 62)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 87)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 88)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 89)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 114)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 115)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 116)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 141)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 142)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 143)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 168)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 169)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 170)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 195)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 196)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 197)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 9)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 10)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 11)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 36)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 37)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 38)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 63)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 64)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 65)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 90)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 91)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 92)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 117)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 118)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 119)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 144)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 145)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 146)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 171)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 172)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 173)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 198)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 199)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 200)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 12)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 13)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 14)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 39)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 40)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 41)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 66)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 67)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 68)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 93)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 94)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 95)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 120)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 121)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 122)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 147)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 148)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 149)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 174)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 175)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 176)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 201)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 202)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 203)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 15)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 16)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 17)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 42)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 43)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 44)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 69)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 70)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 71)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 96)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 97)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 98)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 123)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 124)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 125)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 150)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 151)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 152)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 177)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 178)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 179)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 204)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 205)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 206)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 18)] * kernel_shared[((((int)threadIdx.x) * 144) + (rc_outer_inner * 72))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 19)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 20)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 45)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 46)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 47)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 72)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 73)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 74)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 99)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 100)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 101)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 126)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 127)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 128)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 153)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 154)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 155)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 180)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 181)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 182)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 207)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 208)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 209)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 3)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 4)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 5)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 30)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 31)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 32)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 57)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 58)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 59)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 84)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 85)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 86)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 111)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 112)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 113)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 138)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 139)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 140)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 165)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 166)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 167)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 192)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 193)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 194)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 6)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 7)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 8)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 33)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 34)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 35)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 60)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 61)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 62)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 87)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 88)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 89)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 114)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 115)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 116)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 141)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 142)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 143)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 168)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 169)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 170)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 195)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 196)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 197)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 9)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 10)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 11)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 36)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 37)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 38)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 63)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 64)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 65)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 90)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 91)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 92)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 117)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 118)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 119)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 144)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 145)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 146)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 171)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 172)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 173)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 198)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 199)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 200)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 12)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 13)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 14)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 39)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 40)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 41)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 66)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 67)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 68)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 93)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 94)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 95)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 120)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 121)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 122)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 147)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 148)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 149)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 174)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 175)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 176)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 201)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 202)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 203)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 15)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 16)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 17)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 42)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 43)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 44)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 69)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 70)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 71)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 96)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 97)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 98)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 123)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 124)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 125)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 150)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 151)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 152)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 177)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 178)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 179)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 204)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 205)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 206)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 18)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 19)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 20)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 45)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 46)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 47)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 72)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 73)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 74)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 99)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 100)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 101)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 126)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 127)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 128)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 153)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 154)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 155)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 180)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 181)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 182)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 207)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 208)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 209)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 21)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 22)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 23)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 48)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 49)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 50)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 75)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 76)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 77)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 102)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 103)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 104)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 129)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 130)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 131)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 156)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 157)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 158)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 183)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 184)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 185)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 210)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 211)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 212)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 6)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 7)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 8)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 33)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 34)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 35)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 60)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 61)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 62)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 87)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 88)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 89)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 114)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 115)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 116)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 141)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 142)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 143)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 168)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 169)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 170)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 195)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 196)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 216) + 197)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 9)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 10)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 11)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 36)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 37)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 38)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 63)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 64)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 65)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 90)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 91)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 92)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 117)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 118)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 119)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 144)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 145)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 146)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 171)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 172)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 173)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 198)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 199)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 216) + 200)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 12)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 13)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 14)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 39)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 40)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 41)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 66)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 67)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 68)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 93)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 94)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 95)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 120)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 121)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 122)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 147)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 148)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 149)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 174)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 175)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 176)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 201)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 202)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 216) + 203)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 15)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 16)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 17)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 42)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 43)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 44)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 69)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 70)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 71)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 96)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 97)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 98)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 123)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 124)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 125)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 150)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 151)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 152)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 177)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 178)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 179)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 204)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 205)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 216) + 206)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 18)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 19)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 20)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 45)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 46)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 47)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 72)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 73)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 74)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 99)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 100)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 101)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 126)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 127)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 128)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 153)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 154)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 155)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 180)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 181)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 182)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 207)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 208)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 216) + 209)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 21)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 22)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 23)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 48)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 49)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 50)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 75)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 76)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 77)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 102)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 103)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 104)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 129)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 130)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 131)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 156)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 157)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 158)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 183)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 184)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 185)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 210)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 211)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 216) + 212)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 24)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 25)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 26)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 51)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 52)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 53)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 78)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 79)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 80)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 105)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 106)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 107)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 132)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 133)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 134)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 159)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 160)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 161)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 186)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 187)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 188)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 213)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 214)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 216) + 215)] * kernel_shared[(((((int)threadIdx.x) * 144) + (rc_outer_inner * 72)) + 71)]));
}
}
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ }
}
</pre></div>
</div>
@@ -1580,7 +2377,7 @@ 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 33.283 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 46.350 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 572268b1fb..970009e3f0 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)
- 8.2236 8.2198 8.2359 8.2150 0.0089
+ 8.1964 8.1980 8.2093 8.1820 0.0112
</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 3.131 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.856 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 cf2905c26e..f4d084373f 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)
- 755.0832 754.4683 758.7039 752.0773 2.7400
+ 760.4773 760.9756 761.2818 759.1745 0.9296
</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 32.024 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.897 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 70f69cbe18..a5d0992641 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,32 +632,217 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[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
+ compute_5[(cse_var_1 + 32)] = 0f32
+ compute_5[(cse_var_1 + 33)] = 0f32
+ compute_5[(cse_var_1 + 34)] = 0f32
+ compute_5[(cse_var_1 + 35)] = 0f32
+ compute_5[(cse_var_1 + 36)] = 0f32
+ compute_5[(cse_var_1 + 37)] = 0f32
+ compute_5[(cse_var_1 + 38)] = 0f32
+ compute_5[(cse_var_1 + 39)] = 0f32
+ compute_5[(cse_var_1 + 40)] = 0f32
+ compute_5[(cse_var_1 + 41)] = 0f32
+ compute_5[(cse_var_1 + 42)] = 0f32
+ compute_5[(cse_var_1 + 43)] = 0f32
+ compute_5[(cse_var_1 + 44)] = 0f32
+ compute_5[(cse_var_1 + 45)] = 0f32
+ compute_5[(cse_var_1 + 46)] = 0f32
+ compute_5[(cse_var_1 + 47)] = 0f32
+ compute_5[(cse_var_1 + 64)] = 0f32
+ compute_5[(cse_var_1 + 65)] = 0f32
+ compute_5[(cse_var_1 + 66)] = 0f32
+ compute_5[(cse_var_1 + 67)] = 0f32
+ compute_5[(cse_var_1 + 68)] = 0f32
+ compute_5[(cse_var_1 + 69)] = 0f32
+ compute_5[(cse_var_1 + 70)] = 0f32
+ compute_5[(cse_var_1 + 71)] = 0f32
+ compute_5[(cse_var_1 + 72)] = 0f32
+ compute_5[(cse_var_1 + 73)] = 0f32
+ compute_5[(cse_var_1 + 74)] = 0f32
+ compute_5[(cse_var_1 + 75)] = 0f32
+ compute_5[(cse_var_1 + 76)] = 0f32
+ compute_5[(cse_var_1 + 77)] = 0f32
+ compute_5[(cse_var_1 + 78)] = 0f32
+ compute_5[(cse_var_1 + 79)] = 0f32
+ compute_5[(cse_var_1 + 96)] = 0f32
+ compute_5[(cse_var_1 + 97)] = 0f32
+ compute_5[(cse_var_1 + 98)] = 0f32
+ compute_5[(cse_var_1 + 99)] = 0f32
+ compute_5[(cse_var_1 + 100)] = 0f32
+ compute_5[(cse_var_1 + 101)] = 0f32
+ compute_5[(cse_var_1 + 102)] = 0f32
+ compute_5[(cse_var_1 + 103)] = 0f32
+ compute_5[(cse_var_1 + 104)] = 0f32
+ compute_5[(cse_var_1 + 105)] = 0f32
+ compute_5[(cse_var_1 + 106)] = 0f32
+ compute_5[(cse_var_1 + 107)] = 0f32
+ compute_5[(cse_var_1 + 108)] = 0f32
+ compute_5[(cse_var_1 + 109)] = 0f32
+ compute_5[(cse_var_1 + 110)] = 0f32
+ compute_5[(cse_var_1 + 111)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ let cse_var_67: int32 = (i.outer.inner*1024)
+ let cse_var_66: int32 = (elem_idx*16)
+ let cse_var_65: int32 = (cse_var_1 + 99)
+ let cse_var_64: int32 = (cse_var_1 + 98)
+ let cse_var_63: int32 = (cse_var_1 + 97)
+ let cse_var_62: int32 = (cse_var_1 + 96)
+ let cse_var_61: int32 = (cse_var_1 + 9)
+ let cse_var_60: int32 = (cse_var_1 + 8)
+ let cse_var_59: int32 = (cse_var_1 + 79)
+ let cse_var_58: int32 = (cse_var_1 + 78)
+ let cse_var_57: int32 = (cse_var_1 + 77)
+ let cse_var_56: int32 = (cse_var_1 + 76)
+ let cse_var_55: int32 = (cse_var_1 + 75)
+ let cse_var_54: int32 = (cse_var_1 + 74)
+ let cse_var_53: int32 = (cse_var_1 + 73)
+ let cse_var_52: int32 = (cse_var_1 + 72)
+ let cse_var_51: int32 = (cse_var_1 + 71)
+ let cse_var_50: int32 = (cse_var_1 + 70)
+ let cse_var_49: int32 = (cse_var_1 + 7)
+ let cse_var_48: int32 = (cse_var_1 + 69)
+ let cse_var_47: int32 = (cse_var_1 + 68)
+ let cse_var_46: int32 = (cse_var_1 + 67)
+ let cse_var_45: int32 = (cse_var_1 + 66)
+ let cse_var_44: int32 = (cse_var_1 + 65)
+ let cse_var_43: int32 = (cse_var_1 + 64)
+ let cse_var_42: int32 = (cse_var_1 + 6)
+ let cse_var_41: int32 = (cse_var_1 + 5)
+ let cse_var_40: int32 = (cse_var_1 + 47)
+ let cse_var_39: int32 = (cse_var_1 + 46)
+ let cse_var_38: int32 = (cse_var_1 + 45)
+ let cse_var_37: int32 = (cse_var_1 + 44)
+ let cse_var_36: int32 = (cse_var_1 + 43)
+ let cse_var_35: int32 = (cse_var_1 + 42)
+ let cse_var_34: int32 = (cse_var_1 + 41)
+ let cse_var_33: int32 = (cse_var_1 + 40)
+ let cse_var_32: int32 = (cse_var_1 + 4)
+ let cse_var_31: int32 = (cse_var_1 + 39)
+ let cse_var_30: int32 = (cse_var_1 + 38)
+ let cse_var_29: int32 = (cse_var_1 + 37)
+ let cse_var_28: int32 = (cse_var_1 + 36)
+ let cse_var_27: int32 = (cse_var_1 + 35)
+ let cse_var_26: int32 = (cse_var_1 + 34)
+ let cse_var_25: int32 = (cse_var_1 + 33)
+ let cse_var_24: int32 = (cse_var_1 + 32)
+ let cse_var_23: int32 = (cse_var_1 + 3)
+ let cse_var_22: int32 = (cse_var_1 + 2)
+ let cse_var_21: int32 = (cse_var_1 + 15)
+ let cse_var_20: int32 = (cse_var_1 + 14)
+ let cse_var_19: int32 = (cse_var_1 + 13)
+ let cse_var_18: int32 = (cse_var_1 + 12)
+ let cse_var_17: int32 = (cse_var_1 + 111)
+ let cse_var_16: int32 = (cse_var_1 + 110)
+ let cse_var_15: int32 = (cse_var_1 + 11)
+ let cse_var_14: int32 = (cse_var_1 + 109)
+ let cse_var_13: int32 = (cse_var_1 + 108)
+ let cse_var_12: int32 = (cse_var_1 + 107)
+ let cse_var_11: int32 = (cse_var_1 + 106)
+ let cse_var_10: int32 = (cse_var_1 + 105)
+ let cse_var_9: int32 = (cse_var_1 + 104)
+ let cse_var_8: int32 = (cse_var_1 + 103)
+ let cse_var_7: int32 = (cse_var_1 + 102)
+ let cse_var_6: int32 = (cse_var_1 + 101)
+ let cse_var_5: int32 = (cse_var_1 + 100)
+ let cse_var_4: int32 = (cse_var_1 + 10)
+ let cse_var_3: int32 = (cse_var_1 + 1)
+ {
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
- }
+ let cse_var_68: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -695,7 +880,7 @@ 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: 1.634 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.028 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 d57e22dd7b..1a4a8b16cc 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">ΒΆ</a></h1>
-<p><strong>00:35.180</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:36.592</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,22 +349,22 @@
</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>00:35.145</p></td>
+<td><p>00:36.555</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.022</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 d4681e27cd..84aaae563c 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,7 +689,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1127076
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5936006
No: 2 GFLOPS: 0.00/0.00 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)
@@ -812,7 +812,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6215972
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5966431
No: 3 GFLOPS: 0.00/0.00 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)
@@ -935,7 +935,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3045668
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5553765
No: 4 GFLOPS: 0.00/0.00 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)
@@ -1058,9 +1058,9 @@ 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, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6221353
-No: 5 GFLOPS: 47.85/47.85 result: MeasureResult(costs=(0.004837766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6264150142669678, timestamp=1667942409.181963) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2592560
-No: 6 GFLOPS: 0.00/47.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2903595
+No: 5 GFLOPS: 363.62/363.62 result: MeasureResult(costs=(0.0006366531333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8916919231414795, timestamp=1667947565.4115362) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9530840
+No: 6 GFLOPS: 0.00/363.62 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
@@ -1182,9 +1182,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10210354
-No: 7 GFLOPS: 52.95/52.95 result: MeasureResult(costs=(0.004371859304347826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6112711429595947, timestamp=1667942410.7586637) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 7, 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', 1500), ('unroll_explicit', 0)],None,4936373
-No: 8 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2542109
+No: 7 GFLOPS: 193.97/363.62 result: MeasureResult(costs=(0.0011935006592592593,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7467830181121826, timestamp=1667947566.387904) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1891640
+No: 8 GFLOPS: 3.89/363.62 result: MeasureResult(costs=(0.05947156125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2675788402557373, timestamp=1667947567.504721) [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,50272
+No: 9 GFLOPS: 0.00/363.62 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
@@ -1306,8 +1307,8 @@ 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, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8634708
-No: 9 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+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, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8082442
+No: 10 GFLOPS: 0.00/363.62 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
@@ -1429,8 +1430,8 @@ 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, 16, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,339284
-No: 10 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1285173
+No: 11 GFLOPS: 0.00/363.62 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
@@ -1552,8 +1553,8 @@ 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, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8322319
-No: 11 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,419124
+No: 12 GFLOPS: 0.00/363.62 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
@@ -1675,9 +1676,9 @@ 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, 32, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,510697
-No: 12 GFLOPS: 8.74/52.95 result: MeasureResult(costs=(0.0264729595,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.278751850128174, timestamp=1667942419.2637608) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4999301
-No: 13 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10199016
+No: 13 GFLOPS: 2.07/363.62 result: MeasureResult(costs=(0.11171890999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.094568967819214, timestamp=1667947570.947638) [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3136183
+No: 14 GFLOPS: 0.00/363.62 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
@@ -1799,8 +1800,8 @@ 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6832781
-No: 14 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4996092
+No: 15 GFLOPS: 0.00/363.62 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
@@ -1922,8 +1923,8 @@ 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, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4994568
-No: 15 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,116374
+No: 16 GFLOPS: 0.00/363.62 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
@@ -2045,9 +2046,8 @@ 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, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3818192
-No: 16 GFLOPS: 2.24/52.95 result: MeasureResult(costs=(0.10320736675,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.392850637435913, timestamp=1667942421.8846374) [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5349706
-No: 17 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10012317
+No: 17 GFLOPS: 0.00/363.62 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
@@ -2169,8 +2169,26 @@ 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, 256, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5579739
-No: 18 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,407077
+No: 18 GFLOPS: 0.00/363.62 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8807709
+No: 19 GFLOPS: 0.00/363.62 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
@@ -2292,8 +2310,8 @@ 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, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1856760
-No: 19 GFLOPS: 0.00/52.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2505608
+No: 20 GFLOPS: 0.00/363.62 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
@@ -2415,130 +2433,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7578505
-No: 20 GFLOPS: 0.00/52.95 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:388
- 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:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 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:388
- 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:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 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, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1065067
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8110720
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2577,9 +2472,9 @@ 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, 8, 2, 1]), ('tile_y', [-1, 1, 7, 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', 1500), ('unroll_explicit', 0)],None,4936373
+[('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9530840
Finish loading 20 records
-Time cost of this operator: 0.004712
+Time cost of this operator: 0.000914
</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 53410ae3e7..104d0f75d0 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 309.8 98.64 (1, 2, 10, 10, 3) 2 1 [309.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.141 1.0 (1, 6, 10, 10) 1 1 [3.141]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.13 0.36 (1, 1, 10, 10, 3) 1 1 [1.13]
-Total_time - 314.071 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.1 98.715 (1, 2, 10, 10, 3) 2 1 [311.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.978 (1, 6, 10, 10) 1 1 [3.082]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.308 (1, 1, 10, 10, 3) 1 1 [0.969]
+Total_time - 315.151 - - - - -
</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 136.7 98.111 (1, 6, 10, 10, 1) 2 1 [136.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.775 1.274 (1, 6, 10, 10) 1 1 [1.775]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.857 0.615 (1, 3, 10, 10, 1) 1 1 [0.857]
-Total_time - 139.332 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.503 (1, 6, 10, 10, 1) 2 1 [102.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.773 1.684 (1, 6, 10, 10) 1 1 [1.773]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.856 0.813 (1, 3, 10, 10, 1) 1 1 [0.856]
+Total_time - 105.33 - - - - -
</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 9fdb848e89..2868c4c30c 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/tmpoh3r_kju/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmps1or2jlt/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/tmpoh3r_kju/images/target contains 8144 images
-/tmp/tmpoh3r_kju/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [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/tmps1or2jlt/images/target contains 8144 images
+/tmp/tmps1or2jlt/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: 0.2316 - accuracy: 0.9163 - val_loss: 0.1270 - val_accuracy: 0.9603 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2297 - accuracy: 0.9187 - val_loss: 0.1226 - val_accuracy: 0.9634 - 47s/epoch - 142ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.1021 - accuracy: 0.9614 - val_loss: 0.1203 - val_accuracy: 0.9664 - 44s/epoch - 134ms/step
+328/328 - 43s - loss: 0.0974 - accuracy: 0.9650 - val_loss: 0.1075 - val_accuracy: 0.9668 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0670 - accuracy: 0.9762 - val_loss: 0.1376 - val_accuracy: 0.9588 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0655 - accuracy: 0.9754 - val_loss: 0.1182 - val_accuracy: 0.9581 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7fdfa469b510>
+<keras.callbacks.History object at 0x7efb7c131cd0>
</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 TVMβs autotuning capabilities</a> to dramatically improve the modelβs performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 33.541 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 18.321 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 724a56a266..71520f1e69 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">ΒΆ</a></h1>
-<p><strong>05:34.359</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:20.260</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>04:33.541</p></td>
+<td><p>04:18.321</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>00:48.920</p></td>
+<td><p>00:50.126</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>00:08.204</p></td>
+<td><p>00:07.927</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>00:03.692</p></td>
+<td><p>00:03.884</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 f096285289..fe1bf1448d 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">ΒΆ</a></h1>
-<p><strong>00:43.473</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.249</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.796</p></td>
+<td><p>00:32.502</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>00:10.137</p></td>
+<td><p>00:10.349</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>00:01.533</p></td>
+<td><p>00:01.391</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 fe3f8e8bdc..e150266168 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 0x7fdf48c11050>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7efb7c4787a0>
</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 618016b642..00c30ed96b 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">ΒΆ</a></h1>
-<p><strong>00:06.457</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.514</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>00:04.161</p></td>
+<td><p>00:05.079</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>00:00.977</p></td>
+<td><p>00:01.065</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>00:00.558</p></td>
+<td><p>00:00.588</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>00:00.540</p></td>
+<td><p>00:00.569</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>00:00.124</p></td>
+<td><p>00:00.116</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>00:00.048</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 223aecc3fb..cd109d9318 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/tmp22fhpqe4/input0.cc'\nsource_filename = \"/tmp/tmp22fhpqe4/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/tmp362bexjz/input0.cc'\nsource_filename = \"/tmp/tmp362bexjz/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 1224542ef2..77bb7b4f16 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 3f2f76b031..f640c5e5ce 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/750ba9f74/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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 611b6cb401..8fdfe9c38f 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/750ba9f74/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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 6c397c174c..ab34981bc8 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/750ba9f74/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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 d820587e1a..5c1fc04cb6 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/750ba9f74/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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 30fedecf2d..d89542ce62 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/750ba9f74/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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 a13b85d90d..63b5497aa1 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/750ba9f74/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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/750ba9f74/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/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 045a50f0ff..95e88d73f3 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/750ba9f74/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 0718ce22bb..103dfed264 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/750ba9f74/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/16bb1a6c2/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
... 2223 lines suppressed ...