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 2022/11/15 23:02:22 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@72c60ad78a4cd9ca055f567ffd762462a2b85428)
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 086016facc deploying docs (apache/tvm@72c60ad78a4cd9ca055f567ffd762462a2b85428)
086016facc is described below
commit 086016facce80571c1af9269f85ac3a95921ba45
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Nov 15 23:02:15 2022 +0000
deploying docs (apache/tvm@72c60ad78a4cd9ca055f567ffd762462a2b85428)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 293847 -> 324292 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22348 -> 23851 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 | 9 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2064 +++++++++-----------
.../tune_network_cuda.rst.txt | 7 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 88 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 209 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 7 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
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 | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 12 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 41 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../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 | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2064 +++++++++-----------
.../tune_with_autoscheduler/tune_network_cuda.html | 3 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 88 +-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 209 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 265 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 30 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
127 files changed, 2992 insertions(+), 3345 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 71e241b4ac..fd04aec899 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 20e0aa607a..176d23232e 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 75dc2174b5..327fb57387 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 9.497 seconds)
+ **Total running time of the script:** ( 1 minutes 11.320 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 067953a638..ef926d6d0c 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 897ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 898ms/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 b8836b0a2a..4695cedde3 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.zip373cb7f9-7286-4191-b489-20f6ef85a8b5 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip30a3716f-a568-48cd-8d26-7c74d34e71e5 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 cbab28a797..58997587b0 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 43.4MB/s]
25%|##5 | 10.5M/41.5M [00:00<00:00, 38.3MB/s]
34%|###3 | 14.1M/41.5M [00:00<00:00, 36.1MB/s]
42%|####2 | 17.5M/41.5M [00:00<00:00, 32.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.5MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 40.4MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 42.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 39.4MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 44.7MB/s]
26%|##5 | 10.6M/41.5M [00:00<00:00, 40.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 30.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 38.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 47.3MB/s]
94%|#########3| 39.0M/41.5M [00:00<00:00, 53.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 45.6MB/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 2311b8f003..016afeae83 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 78.8MB/s]
45%|####5 | 20.3M/44.7M [00:00<00:00, 107MB/s]
71%|####### | 31.7M/44.7M [00:00<00:00, 101MB/s]
93%|#########2| 41.4M/44.7M [00:00<00:00, 96.8MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 102MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 43.7MB/s]
32%|###2 | 14.3M/44.7M [00:00<00:00, 44.2MB/s]
41%|####1 | 18.5M/44.7M [00:00<00:00, 43.9MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 48.0MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 52.8MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 47.4MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 50.4MB/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 b96a1bd581..a0a8198e29 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 6.876 seconds)
+ **Total running time of the script:** ( 1 minutes 9.717 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 d4eb3ccac1..91bc64c82c 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
=================
-**05:30.501** total execution time for **how_to_compile_models** files:
+**05:42.135** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.497 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.320 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:06.876 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:09.717 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:44.418 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:44.703 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.418 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.266 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:27.771 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.669 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:24.917 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.046 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:23.707 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.537 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.395 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.783 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.206 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.722 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.295 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.374 | 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 2c2830a66a..299be05b79 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)
- 14.3773 14.2811 14.8635 13.9957 0.3353
+ 15.8386 15.8180 15.9869 15.7274 0.0865
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 24b64afa0e..52bdb3bf89 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:04, 36.0MB/s]
6%|5 | 9.74M/170M [00:00<00:05, 33.3MB/s]
8%|8 | 14.3M/170M [00:00<00:04, 38.6MB/s]
11%|# | 18.1M/170M [00:00<00:04, 38.7MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 45.1MB/s]
18%|#7 | 30.3M/170M [00:00<00:02, 49.6MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 60.0MB/s]
27%|##7 | 46.3M/170M [00:01<00:02, 52.9MB/s]
31%|###1 | 52.9M/170M [00:01<00:02, 57.2MB/s]
37%|###6 | 62.3M/170M [00:01<00:01, 64.3MB/s]
40%|#### | 68.5M/170M [00:01<00:01, 62.3MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 72.9MB/s]
51%|#####1 | 87.0M/170M [00:01<00:01, 67.3MB/s]
56%|#####5 | 94.3M/170M [00:01<00:01, 59.5MB/s]
59%|#####8 | 100M/170M [00:01<00:01, 49.0MB/s]
66%|######5 | 112M/170M [00:02<00:00, 65.4MB/s]
71%|####### | 120M/170M [00:02<00:00, 67.2MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 61.8MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 59.2MB/s]
85%|########4 | 144M/170M [00:02<00:00, 66.1MB/s]
94%|#########4| 160M/170M [00:02<00:00, 83.9MB/s]
99%|#########9| 168M/170M [00:02<00:00, 73.2MB/s]
100%|##########| 170M/170M [00:02<00:00, 61.5MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 8.16M/170M [00:00<00:01, 85.6MB/s]
10%|9 | 16.3M/170M [00:00<00:02, 70.3MB/s]
18%|#8 | 30.6M/170M [00:00<00:01, 103MB/s]
25%|##5 | 42.6M/170M [00:00<00:01, 111MB/s]
32%|###1 | 53.5M/170M [00:00<00:01, 110MB/s]
38%|###7 | 64.3M/170M [00:00<00:01, 97.3MB/s]
45%|####4 | 75.8M/170M [00:00<00:00, 104MB/s]
52%|#####1 | 88.0M/170M [00:00<00:00, 102MB/s]
59%|#####8 | 100M/170M [00:01<00:00, 109MB/s]
65%|######5 | 111M/170M [00:01<00:00, 110MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 97.8MB/s]
78%|#######8 | 133M/170M [00:01<00:00, 104MB/s]
84%|########4 | 143M/170M [00:01<00:00, 93.1MB/s]
90%|########9 | 153M/170M [00:01<00:00, 79.7MB/s]
95%|#########4| 161M/170M [00:01<00:00, 80.7MB/s]
100%|##########| 170M/170M [00:01<00:00, 95.9MB/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:** ( 2 minutes 50.960 seconds)
+ **Total running time of the script:** ( 3 minutes 8.547 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 bd359c0e06..8158c8b2fb 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]
100%|##########| 13.6M/13.6M [00:00<00:00, 147MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
88%|########7 | 11.9M/13.6M [00:00<00:00, 125MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 119MB/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)
- 82.3219 82.2874 83.2065 82.0870 0.1842
+ 90.3223 90.2844 93.1309 89.9646 0.3712
@@ -465,6 +465,11 @@ Deploy a quantized TFLite Model
TODO
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 4.532 seconds)
+
+
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized.py:
.. only:: html
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 9ef6277358..948da77a89 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)
- 107.5040 107.4360 109.3455 107.1018 0.2973
+ 120.0354 120.0333 121.9064 119.1732 0.3621
@@ -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 16.823 seconds)
+ **Total running time of the script:** ( 2 minutes 30.960 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 096358a9a5..ba4a2d98c9 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 39.758 seconds)
+ **Total running time of the script:** ( 1 minutes 42.602 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 356cba950f..93826a0428 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]
3%|3 | 4057/132723 [00:00<00:03, 40564.82KB/s]
10%|9 | 13146/132723 [00:00<00:01, 70164.58KB/s]
17%|#6 | 22555/132723 [00:00<00:01, 81085.21KB/s]
24%|##4 | 31887/132723 [00:00<00:01, 85912.88KB/s]
30%|### | 40479/132723 [00:00<00:01, 68726.11KB/s]
37%|###7 | 49280/132723 [00:00<00:01, 74261.16KB/s]
44%|####4 | 58704/132723 [00:00<00:00, 80133.40KB/s]
51%|##### | 67044/132723 [00:00<00:00, 79029.05KB/s]
58%|#####7 | 76466/132723 [00:00<00:00, 83457.16KB/s]
64%|######4 | 84996/132723 [00:01<00:00, 72536.70KB/s]
71%|####### | 94016/132723 [00:01<00:00, 77237.83KB/s]
77%|#######6 | 102057/132723 [00:01<00:00, 71950.25KB/s]
84%|########3 | 111459/132723 [00:01<00:00, 77821.66KB/s]
91%|#########1| 120885/132723 [00:01<00:00, 82348.32KB/s]
98%|#########8| 130270/132723 [00:01<00:00, 85593.32KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 78465.13KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5211/132723 [00:00<00:02, 52093.28KB/s]
10%|9 | 12718/132723 [00:00<00:01, 65605.13KB/s]
15%|#4 | 19279/132723 [00:00<00:02, 52580.85KB/s]
20%|#9 | 26328/132723 [00:00<00:01, 58727.43KB/s]
25%|##4 | 32757/132723 [00:00<00:01, 52957.70KB/s]
29%|##8 | 38282/132723 [00:00<00:01, 52056.09KB/s]
34%|###4 | 45641/132723 [00:00<00:01, 58250.21KB/s]
40%|#### | 53113/132723 [00:00<00:01, 63040.71KB/s]
46%|####5 | 60534/132723 [00:01<00:01, 66320.03KB/s]
51%|#####1 | 68294/132723 [00:01<00:00, 69652.38KB/s]
57%|#####7 | 76171/132723 [00:01<00:00, 72358.61KB/s]
63%|######3 | 84073/132723 [00:01<00:00, 74339.68KB/s]
69%|######9 | 91874/132723 [00:01<00:00, 75433.12KB/s]
75%|#######5 | 99784/132723 [00:01<00:00, 76528.30KB/s]
81%|########1 | 107636/132723 [00:01<00:00, 77122.79KB/s]
87%|########6
| 115372/132723 [00:01<00:00, 73752.62KB/s]
93%|#########2| 122794/132723 [00:01<00:00, 72408.36KB/s]
98%|#########8| 130522/132723 [00:01<00:00, 73813.67KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67529.47KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 43.459 seconds)
+ **Total running time of the script:** ( 2 minutes 58.422 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 0d56524076..d89b8344d2 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
=================
-**11:52.991** total execution time for **how_to_deploy_models** files:
+**12:51.084** 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``) | 02:50.960 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:08.547 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:43.459 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:58.422 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:16.823 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.960 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:39.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.602 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 00:59.785 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:04.532 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.165 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.021 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.257 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.292 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.778 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.703 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 502d383fd9..f172e38a50 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.zip7fd70611-97df-460a-987e-4039ce1c77f7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8c5bc586-cbca-4d15-8a97-a7d74d35ff2e 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 ea825fd44c..d70f919c11 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
=================
-**00:43.008** total execution time for **how_to_extend_tvm** files:
+**00:46.789** 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``) | 00:39.959 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.371 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.127 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.385 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.915 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.025 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 9be13c8788..387eb46eb9 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: 6762us [6762us] (46.54%; 46.54%)
- FoldScaleAxis: 7767us [6us] (53.46%; 53.46%)
- FoldConstant: 7761us [1619us] (53.42%; 99.92%)
- InferType: 6142us [6142us] (42.27%; 79.14%)
+ InferType: 7131us [7131us] (44.88%; 44.88%)
+ FoldScaleAxis: 8757us [22us] (55.12%; 55.12%)
+ FoldConstant: 8734us [1703us] (54.98%; 99.74%)
+ InferType: 7031us [7031us] (44.25%; 80.50%)
@@ -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: 6238us [6238us] (45.07%; 45.07%)
- FoldScaleAxis: 7603us [4us] (54.93%; 54.93%)
- FoldConstant: 7598us [1507us] (54.90%; 99.94%)
- InferType: 6092us [6092us] (44.01%; 80.17%)
+ InferType: 6653us [6653us] (45.13%; 45.13%)
+ FoldScaleAxis: 8089us [5us] (54.87%; 54.87%)
+ FoldConstant: 8084us [1669us] (54.84%; 99.94%)
+ InferType: 6415us [6415us] (43.51%; 79.35%)
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 42baf1956e..abdf89afd7 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.145023 ms
+ Convolution: 54.130718 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 a40e280dc1..54a473b348 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: 6.842969 ms
+ conv2d with tensor core: 9.118951 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 20f3642a46..82002c45c4 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: 0.013832
- Baseline: 3.343903
+ Numpy running time: 0.017861
+ Baseline: 3.252491
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.272480
+ Opt1: 0.301002
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.302276
+ Opt2: 0.336036
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.104893
+ Opt3: 0.114605
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.099920
+ Opt4: 0.109476
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.094371
+ Opt5: 0.112047
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.122287
+ Opt6: 0.146412
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 97042bbcb4..c0d472a18a 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
=================
-**00:31.486** total execution time for **how_to_optimize_operators** files:
+**00:34.078** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:29.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.714 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.307 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.357 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.081 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.007 | 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 90f5d686a8..3f8bb3e16c 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
=================
-**08:29.382** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:03.587** 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``) | 05:18.071 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:37.277 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:24.356 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.794 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:57.802 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.709 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.267 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.091 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:10.818 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.767 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.068 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.949 | 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 afcd25f658..5431fe9385 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,12 +240,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -253,645 +253,470 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*3136)
- let cse_var_1: int32 = (rc.outer.outer*576)
+ 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" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 335)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 735), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 833), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 678)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 931), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1029), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1127), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1225), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1021)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1421), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1519), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1617), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1715), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1813), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1911), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2009), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2058), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2107), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1707)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2254), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2303), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2401), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2450), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2499), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2597)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2597), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2646)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 2050)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2695)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2695), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2793)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2793), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2842)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2842), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2891)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2891), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2989)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2989), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3038)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3038), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3087)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 2393)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3185)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3185), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3234)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3234), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3283)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3283), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3381)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3381), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3430)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3430), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3479)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3479), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 2736)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3577)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3577), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3626)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3626), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3675)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3675), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3773)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3773), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3822)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3822), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3871)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3871), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3969)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 3079)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 4018)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 4018), 63)*49)) + rx.outer.outer) + threadIdx.x_1) + 41)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 49), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 53), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 34)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 151), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 19)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 106), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 155), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 61), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 53), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 833)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 833), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 65), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 882), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 38)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 931)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 931), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 163), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 980), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1029)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1029), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 23)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1078), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 118), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1127)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1127), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 167), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1225)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1225), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 73), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1274), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 122), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1323)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1323), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 57), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1372), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1421)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1421), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 77), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1470), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 42)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 17), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1519)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1519), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 175), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ff.outer.inner: int32, 0, 2) {
- let cse_var_7: int32 = (ff.outer.inner*4)
- let cse_var_6: int32 = (cse_var_7 + 3)
- let cse_var_5: int32 = (cse_var_7 + 2)
- let cse_var_4: int32 = (cse_var_7 + 1)
- let cse_var_3: int32 = ((ff.outer.inner*768) + (rc.outer.inner*96))
- {
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[cse_var_3]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 192)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 384)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 576)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 1)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 193)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 385)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 577)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 2)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 194)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 386)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 578)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 3)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 195)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 387)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 579)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 4)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 196)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 388)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 580)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 5)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 197)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 389)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 581)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 6)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 198)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 390)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 582)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 7)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 199)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 391)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 583)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 8)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 200)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 392)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 584)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 9)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 201)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 393)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 585)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 10)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 202)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 394)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 586)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 11)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 203)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 395)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 587)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 12)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 204)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 396)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 588)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 13)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 205)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 397)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 589)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 14)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 206)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 398)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 590)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 15)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 207)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 399)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 591)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 16)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 208)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 400)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 592)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 17)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 209)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 401)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 593)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 18)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 210)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 402)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 594)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 19)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 211)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 403)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 595)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 20)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 212)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 404)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 596)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 21)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 213)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 405)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 597)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 22)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 214)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 406)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 598)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 23)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 215)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 407)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 599)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 24)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 216)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 408)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 600)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 25)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 217)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 409)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 601)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 26)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 218)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 410)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 602)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 27)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 219)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 411)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 603)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 28)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 220)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 412)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 604)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 29)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 221)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 413)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 605)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 30)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 222)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 414)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 606)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 31)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 223)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 415)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 607)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 32)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 224)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 416)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 608)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 33)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 225)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 417)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 609)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 34)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 226)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 418)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 610)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 35)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 227)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 419)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 611)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 36)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 228)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 420)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 612)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 37)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 229)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 421)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 613)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 38)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 230)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 422)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 614)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 39)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 231)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 423)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 615)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 40)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 232)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 424)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 616)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 41)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 233)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 425)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 617)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 42)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 234)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 426)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 618)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 43)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 235)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 427)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 619)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 44)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 236)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 428)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 620)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 45)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 237)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 429)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 621)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 46)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 238)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 430)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 622)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 47)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 239)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 431)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 623)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 48)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 240)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 432)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 624)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 49)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 241)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 433)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 625)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 50)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 242)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 434)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 626)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 51)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 243)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 435)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 627)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 52)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 244)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 436)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 628)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 53)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 245)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 437)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 629)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 54)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 246)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 438)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 630)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 55)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 247)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 439)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 631)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 56)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 248)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 440)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 632)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 57)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 249)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 441)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 633)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 58)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 250)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 442)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 634)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 59)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 251)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 443)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 635)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 60)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 252)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 444)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 636)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 61)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 253)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 445)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 637)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 62)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 254)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 446)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 638)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 63)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 255)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 447)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 639)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 64)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 256)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 448)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 640)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 65)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 257)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 449)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 641)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 66)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 258)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 450)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 642)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 67)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 259)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 451)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 643)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 68)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 260)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 452)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 644)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 69)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 261)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 453)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 645)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 70)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 262)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 454)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 646)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 71)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 263)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 455)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 647)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 72)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 264)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 456)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 648)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 73)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 265)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 457)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 649)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 74)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 266)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 458)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 650)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 75)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 267)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 459)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 651)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 76)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 268)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 460)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 652)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 77)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 269)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 461)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 653)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 78)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 270)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 462)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 654)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 79)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 271)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 463)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 655)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 80)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 272)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 464)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 656)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 81)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 273)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 465)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 657)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 82)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 274)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 466)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 658)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 83)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 275)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 467)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 659)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 84)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 276)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 468)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 660)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 85)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 277)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 469)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 661)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 86)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 278)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 470)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 662)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 87)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 279)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 471)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 663)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 88)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 280)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 472)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 664)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 89)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 281)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 473)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 665)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 90)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 282)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 474)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 666)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 91)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 283)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 475)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 667)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 92)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 284)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 476)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 668)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 93)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 285)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 477)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 669)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 94)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 286)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 478)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 670)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 95)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 287)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 479)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 671)]))
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
}
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -946,7 +771,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.242 ms
+ Execution time of this operator: 0.349 ms
@@ -994,36 +819,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1043,12 +868,12 @@ 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=49)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1068,10 +893,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[1536];
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1080,521 +905,418 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ 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();
- pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1707)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2050)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2393)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 3079)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((int)threadIdx.x) < 7) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 63) * 49)) + rx_outer_outer) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
+ 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);
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 49) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 98) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 49) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 53) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 306)];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 151) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 171)];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 106) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 155) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 36)];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 61) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 110) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 53) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 833)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 833) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 65) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 882)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 882) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 342)];
- kernel_shared[(((int)threadIdx.x) + 931)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 931) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 163) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 20) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1029) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 207)];
- kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1078) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 118) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1127) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 167) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1225)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1225) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 73) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1274) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 122) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1323)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1323) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 57) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 28) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1421)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1421) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 77) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1470) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 378)];
- if (((int)threadIdx.x) < 17) {
- kernel_shared[(((int)threadIdx.x) + 1519)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1519) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 175) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ 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);
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[((ff_outer_inner * 768) + (rc_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 192)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 384)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 576)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 193)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 385)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 577)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 194)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 386)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 578)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 195)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 387)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 579)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 196)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 388)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 580)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 197)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 389)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 581)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 198)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 390)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 582)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 199)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 391)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 583)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 200)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 392)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 584)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 201)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 393)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 585)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 202)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 394)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 586)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 203)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 395)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 587)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 204)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 396)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 588)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 205)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 397)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 589)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 206)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 398)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 590)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 207)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 399)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 591)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 208)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 400)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 592)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 209)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 401)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 593)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 210)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 402)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 594)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 211)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 403)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 595)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 212)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 404)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 596)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 213)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 405)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 597)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 214)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 406)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 598)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 215)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 407)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 599)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 216)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 408)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 600)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 217)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 409)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 601)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 218)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 410)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 602)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 219)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 411)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 603)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 220)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 412)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 604)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 221)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 413)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 605)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 222)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 414)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 606)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 223)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 415)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 607)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 224)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 416)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 608)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 225)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 417)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 609)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 226)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 418)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 610)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 227)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 419)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 611)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 228)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 420)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 612)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 229)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 421)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 613)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 230)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 422)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 614)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 231)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 423)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 615)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 232)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 424)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 616)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 233)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 425)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 617)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 234)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 426)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 618)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 235)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 427)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 619)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 236)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 428)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 620)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 237)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 429)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 621)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 238)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 430)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 622)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 239)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 431)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 623)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 240)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 432)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 624)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 241)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 433)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 625)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 242)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 434)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 626)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 243)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 435)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 627)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 244)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 436)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 628)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 245)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 437)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 629)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 246)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 438)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 630)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 247)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 439)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 631)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 248)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 440)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 632)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 249)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 441)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 633)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 250)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 442)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 634)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 251)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 443)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 635)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 252)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 444)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 636)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 253)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 445)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 637)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 254)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 446)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 638)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 255)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 447)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 639)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 256)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 448)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 640)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 257)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 449)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 641)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 258)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 450)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 642)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 259)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 451)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 643)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 260)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 452)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 644)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 261)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 453)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 645)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 262)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 454)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 646)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 263)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 455)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 647)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 264)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 456)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 648)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 265)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 457)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 649)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 266)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 458)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 650)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 267)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 459)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 651)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 268)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 460)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 652)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 269)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 461)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 653)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 270)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 462)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 654)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 271)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 463)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 655)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 272)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 464)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 656)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 273)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 465)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 657)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 274)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 466)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 658)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 275)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 467)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 659)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 276)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 468)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 660)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 277)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 469)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 661)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 278)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 470)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 662)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 279)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 471)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 663)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 280)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 472)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 664)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 281)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 473)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 665)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 282)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 474)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 666)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 283)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 475)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 667)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 284)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 476)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 668)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 285)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 477)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 669)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 286)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 478)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 670)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 287)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 479)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 671)]));
- }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -1656,7 +1378,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 18.071 seconds)
+ **Total running time of the script:** ( 5 minutes 37.277 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 2d1b802fac..6cf6245d82 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)
- 8.1944 8.1998 8.2010 8.1824 0.0085
+ 8.2201 8.2210 8.2265 8.2129 0.0056
@@ -669,6 +669,11 @@ Other Tips
with :any:`auto_scheduler.RPCRunner`.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.709 seconds)
+
+
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
.. only:: html
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 7c8110f4ff..40ad7a70d4 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)
- 678.5120 676.8529 682.4534 676.2298 2.7986
+ 749.5053 749.3239 750.8476 748.3444 1.0299
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 24.356 seconds)
+ **Total running time of the script:** ( 1 minutes 31.794 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 5a73c388e0..453c2c98a9 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,78 +386,32 @@ 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_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = (((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*1024)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) 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_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -513,7 +467,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.813 ms
+ Execution time of this operator: 1.557 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 971f740457..011561cd1b 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
=================
-**00:31.034** total execution time for **how_to_tune_with_autotvm** files:
+**00:40.157** 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``) | 00:31.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:40.122 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.018 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 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``) | 00:00.004 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 4c727bbd8f..205029bfff 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
@@ -265,8 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 7.31/7.31 result: MeasureResult(costs=(0.03165303975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.225941896438599, timestamp=1668547854.2140303) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7446696
- No: 2 GFLOPS: 0.00/7.31 result: Traceback (most recent call last):
+ No: 1 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -388,9 +387,9 @@ 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, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3477247
- No: 3 GFLOPS: 193.61/193.61 result: MeasureResult(costs=(0.0011957172093023257,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.501504421234131, timestamp=1668547855.7061899) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7323425
- No: 4 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7991273
+ No: 2 GFLOPS: 171.39/171.39 result: MeasureResult(costs=(0.0013507484333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.717359781265259, timestamp=1668547719.3734238) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9753105
+ No: 3 GFLOPS: 0.00/171.39 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
@@ -512,8 +511,27 @@ 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, 64, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2573063
- No: 5 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5193914
+ No: 4 GFLOPS: 0.00/171.39 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, 32, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8728613
+ No: 5 GFLOPS: 11.49/171.39 result: MeasureResult(costs=(0.020140954333333332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.108873128890991, timestamp=1668547728.179477) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 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', 512), ('unroll_explicit', 1)],None,7321709
+ No: 6 GFLOPS: 0.00/171.39 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
@@ -635,8 +653,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8214845
- No: 6 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,206850
+ No: 7 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -758,8 +776,9 @@ 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, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,639356
- No: 7 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10439317
+ No: 8 GFLOPS: 55.85/171.39 result: MeasureResult(costs=(0.0041453146,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.635598659515381, timestamp=1668547729.7172017) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2532256
+ No: 9 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -881,9 +900,10 @@ 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, 2, 8, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4966258
- No: 8 GFLOPS: 423.41/423.41 result: MeasureResult(costs=(0.0005467581366120218,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1858747005462646, timestamp=1668547858.8730369) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3940932
- No: 9 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,698557
+ No: 10 GFLOPS: 154.09/171.39 result: MeasureResult(costs=(0.0015023335671641791,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4147913455963135, timestamp=1668547731.5769172) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4743442
+ No: 11 GFLOPS: 3.91/171.39 result: MeasureResult(costs=(0.0591835365,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.168834924697876, timestamp=1668547732.7012928) [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,24131
+ No: 12 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1005,8 +1025,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4579390
- No: 10 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10035867
+ No: 13 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1128,9 +1148,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9154546
- No: 11 GFLOPS: 2.79/423.41 result: MeasureResult(costs=(0.08296199774999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7744982242584229, timestamp=1668547860.8489847) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,693221
- No: 12 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6746441
+ No: 14 GFLOPS: 0.00/171.39 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
@@ -1252,8 +1271,8 @@ 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, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9813377
- No: 13 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9802890
+ No: 15 GFLOPS: 0.00/171.39 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
@@ -1375,8 +1394,8 @@ 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, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2347780
- No: 14 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7048687
+ No: 16 GFLOPS: 0.00/171.39 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
@@ -1498,8 +1517,8 @@ 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, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7526442
- No: 15 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10228449
+ No: 17 GFLOPS: 0.00/171.39 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
@@ -1621,8 +1640,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5744335
- No: 16 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,172090
+ No: 18 GFLOPS: 0.00/171.39 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
@@ -1744,11 +1763,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2845590
- No: 17 GFLOPS: 92.76/423.41 result: MeasureResult(costs=(0.002495668804347826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7457647323608398, timestamp=1668547864.3853936) [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1093919
- No: 18 GFLOPS: 47.65/423.41 result: MeasureResult(costs=(0.00485826580952381,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0213398933410645, timestamp=1668547865.0483766) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10117283
- No: 19 GFLOPS: 168.75/423.41 result: MeasureResult(costs=(0.0013718832837837838,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5751590728759766, timestamp=1668547865.678287) [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3545599
- No: 20 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,573934
+ No: 19 GFLOPS: 0.00/171.39 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
@@ -1870,7 +1886,130 @@ 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, 4, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5674667
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10027704
+ No: 20 GFLOPS: 0.00/171.39 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, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9899368
@@ -1925,9 +2064,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3940932
+ [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9753105
Finish loading 20 records
- Time cost of this operator: 0.000542
+ Time cost of this operator: 0.001456
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 751e1d2164..216eeaf8d4 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 279.7 98.667 (1, 2, 10, 10, 3) 2 1 [279.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.849 1.005 (1, 6, 10, 10) 1 1 [2.849]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.929 0.328 (1, 1, 10, 10, 3) 1 1 [0.929]
- Total_time - 283.478 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.734 (1, 2, 10, 10, 3) 2 1 [310.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.96 (1, 6, 10, 10) 1 1 [3.021]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.306 (1, 1, 10, 10, 3) 1 1 [0.963]
+ Total_time - 314.684 - - - - -
@@ -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 99.438 97.604 (1, 6, 10, 10, 1) 2 1 [99.438]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.586 1.557 (1, 6, 10, 10) 1 1 [1.586]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.855 0.839 (1, 1, 10, 10, 3) 1 1 [0.855]
- Total_time - 101.878 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.9 97.945 (1, 6, 10, 10, 1) 2 1 [134.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.855 1.347 (1, 6, 10, 10) 1 1 [1.855]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.709 (1, 1, 10, 10, 3) 1 1 [0.976]
+ Total_time - 137.731 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 2faf48709d..b12a5dff29 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
23%|##3 | 816k/3.42M [00:00<00:00, 8.31MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 24.1MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 91.1MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -312,6 +312,11 @@ Look up prediction top 1 index in 1000 class synset.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 1.163 seconds)
+
+
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
.. only:: html
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 79fa886b04..db1734badb 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/tmpqr12qxcz/images/random'
+ '/tmp/tmpg5sqjq4r/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpqr12qxcz/images/target contains 8144 images
- /tmp/tmpqr12qxcz/images/random contains 5000 images
+ /tmp/tmpg5sqjq4r/images/target contains 8144 images
+ /tmp/tmpg5sqjq4r/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 41s - loss: 0.2161 - accuracy: 0.9237 - val_loss: 0.1690 - val_accuracy: 0.9411 - 41s/epoch - 126ms/step
+ 328/328 - 46s - loss: 0.2142 - accuracy: 0.9258 - val_loss: 0.1235 - val_accuracy: 0.9558 - 46s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 38s - loss: 0.0862 - accuracy: 0.9669 - val_loss: 0.1181 - val_accuracy: 0.9630 - 38s/epoch - 115ms/step
+ 328/328 - 43s - loss: 0.0909 - accuracy: 0.9664 - val_loss: 0.1908 - val_accuracy: 0.9373 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 38s - loss: 0.0669 - accuracy: 0.9753 - val_loss: 0.1275 - val_accuracy: 0.9573 - 38s/epoch - 115ms/step
+ 328/328 - 43s - loss: 0.0632 - accuracy: 0.9766 - val_loss: 0.1024 - val_accuracy: 0.9645 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7efd81f2ce10>
+ <keras.callbacks.History object at 0x7faadce4d090>
@@ -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 4.321 seconds)
+ **Total running time of the script:** ( 4 minutes 42.678 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 46acbbd57d..48ef0a1469 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**05:56.960** total execution time for **how_to_work_with_microtvm** files:
+**06:43.592** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:04.321 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:42.678 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 00:56.634 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:01.163 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:45.287 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:48.099 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.281 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.998 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.435 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.651 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index e3f14101f0..2e7d85fae4 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
=================
-**00:40.567** total execution time for **how_to_work_with_relay** files:
+**00:42.182** 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``) | 00:29.482 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.696 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.094 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.174 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.985 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.305 | 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 b1c17aeab4..4a2803b25c 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 0x7efdf0147b90>
+ <function my_cuda_math_rule at 0x7fabccc39b00>
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 824a5e863e..525f62f3b0 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.398** total execution time for **how_to_work_with_schedules** files:
+**00:04.297** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.119 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.185 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.880 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.535 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.523 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.514 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.501 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.104 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.045 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.048 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.018 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 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 14898fb035..232eb94839 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/tmpmrfs9xs2/input0.cc'\nsource_filename = \"/tmp/tmpmrfs9xs2/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/tmp_u9dqo0p/input0.cc'\nsource_filename = \"/tmp/tmp_u9dqo0p/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 51638ca72e..9d4800eab0 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:23.694** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:25.564** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:23.688 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.558 | 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 45ac464779..7f0b8f1359 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 25.87s!
+ resnet18_v1 inference graph built in 28.47s!
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 ac43c9c703..667ea61fe5 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 17.62s!
+ yolov3-tiny inference graph built in 19.10s!
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 8d7464d82c..1a9be78ee8 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
=================
-**01:30.918** total execution time for **topic_vta_tutorials_frontend** files:
+**01:39.596** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:46.751 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.303 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.167 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.293 | 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 4ffa6a1116..6316a371ff 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
=================
-**00:02.934** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.062** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.500 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.662 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.434 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.400 | 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 e587a91d95..d65330b1d8 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
=================
-**00:00.773** total execution time for **topic_vta_tutorials** files:
+**00:00.711** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.420 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.387 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.353 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.325 | 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 f111135d3c..ab81fe3968 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 96.149 ms
+ Execution time of this operator: 94.945 ms
@@ -444,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 27.133 seconds)
+ **Total running time of the script:** ( 1 minutes 15.678 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 58a9a98a9e..091bef1c8a 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: 14.86/14.86 result: MeasureResult(costs=(0.018069497400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5381200313568115, timestamp=1668546571.206607) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
- No: 2 GFLOPS: 13.49/14.86 result: MeasureResult(costs=(0.019901616599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5236937999725342, timestamp=1668546571.728785) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
- No: 3 GFLOPS: 13.58/14.86 result: MeasureResult(costs=(0.019765815200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.46259307861328125, timestamp=1668546572.9151666) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
- No: 4 GFLOPS: 9.42/14.86 result: MeasureResult(costs=(0.028481902200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6821160316467285, timestamp=1668546574.2350185) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
- No: 5 GFLOPS: 14.95/14.95 result: MeasureResult(costs=(0.0179531152,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4320809841156006, timestamp=1668546574.793757) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
- No: 6 GFLOPS: 2.32/14.95 result: MeasureResult(costs=(0.1154965488,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.987567663192749, timestamp=1668546577.5080953) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 7 GFLOPS: 4.59/14.95 result: MeasureResult(costs=(0.058530983999999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0897796154022217, timestamp=1668546578.6059496) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
- No: 8 GFLOPS: 1.79/14.95 result: MeasureResult(costs=(0.1497481702,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5677192211151123, timestamp=1668546581.2042096) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 9 GFLOPS: 13.51/14.95 result: MeasureResult(costs=(0.0198727122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4481990337371826, timestamp=1668546582.0871408) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
- No: 10 GFLOPS: 10.53/14.95 result: MeasureResult(costs=(0.025491762,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8611001968383789, timestamp=1668546582.663849) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
+ No: 1 GFLOPS: 0.51/0.51 result: MeasureResult(costs=(0.5272718766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.585996150970459, timestamp=1668546354.1834621) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+ No: 2 GFLOPS: 1.54/1.54 result: MeasureResult(costs=(0.1745524856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.938340425491333, timestamp=1668546357.8866544) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+ No: 3 GFLOPS: 12.74/12.74 result: MeasureResult(costs=(0.021065153,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4743988513946533, timestamp=1668546358.3927968) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
+ No: 4 GFLOPS: 0.90/12.74 result: MeasureResult(costs=(0.2994434038,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.945132493972778, timestamp=1668546364.0808868) [('tile_y', [-1, 128]), ('tile_x', [-1, 2])],None,17
+ No: 5 GFLOPS: 3.93/12.74 result: MeasureResult(costs=(0.0682839642,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.256960391998291, timestamp=1668546365.4600108) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+ No: 6 GFLOPS: 1.22/12.74 result: MeasureResult(costs=(0.21931116020000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.636854887008667, timestamp=1668546369.130447) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+ No: 7 GFLOPS: 2.01/12.74 result: MeasureResult(costs=(0.1332902144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2803597450256348, timestamp=1668546372.1546938) [('tile_y', [-1, 8]), ('tile_x', [-1, 2])],None,13
+ No: 8 GFLOPS: 1.68/12.74 result: MeasureResult(costs=(0.15947188220000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.731454610824585, timestamp=1668546374.920386) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 9 GFLOPS: 2.52/12.74 result: MeasureResult(costs=(0.10667986519999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8241393566131592, timestamp=1668546376.8657906) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+ No: 10 GFLOPS: 2.08/12.74 result: MeasureResult(costs=(0.12878245459999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1800034046173096, timestamp=1668546379.0883493) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 09f23f4f1d..8ce2f46e8b 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': 449.25081586999113, 'median': 449.23343220000334, 'std': 0.34440191044046886}
+ {'mean': 513.4801238399996, 'median': 513.4811045999868, 'std': 1.5907666360712405}
@@ -554,30 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 10.14/ 25.34 GFLOPS | Progress: (4/20) | 7.56 s
[Task 1/25] Current/Best: 18.29/ 25.34 GFLOPS | Progress: (8/20) | 10.01 s
[Task 1/25] Current/Best: 13.97/ 25.34 GFLOPS | Progress: (12/20) | 12.40 s
[Task 1/25] Current/Best: 13.15/ 25.34 GFLOPS | Progress: (16/20) | 14.63 s
[Task 1/25] Current/Best: 18.53/ 25.34 GFLOPS | Progress: (20/20) | 16.16 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 10.56/ 11.95 GFLOPS | Progress: (4/20) | 3.19 s
[Task 2/25] Current/Best: 13.50/ 22.22 GFLOPS | Progress: (8/20) | 4.97 s
[Task 2/25] Current/Best: 23.72/ 23.72 GFLOPS | Progress: (12/20) | 6.19 s
[Task 2/25] Current/Best: 14.56/ 23.72 GFLOPS | Progress: (16/20) | 7.68 s
[Task 2/25] Current/Best: 9.30/ 23.72 GFLOPS | Progress: (20/20) | 9.67 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.06/ 17.53 GFLOPS | Progress: (4/20) | 3.52 s
[Task 3/25] Current/Best: 6.17/ 22.59 GFLOPS | Progress: (8/20) | 6.26 s
[Task 3/25] Current/Best: 19.07/ 22.59 GFLOPS | Progress: (12/20) | 8.31 s
[Task 3/25] Current/Best: 22.82/ 22.82 GFLOPS | Progress: (16/20) | 10.04 s
[Task 3/25] Current/Best: 26.12/ 26.12 GFLOPS | Progress: (20/20) | 11.45 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.82/ 19.17 GFLOPS | Progress: (4/20) | 3.14 s
[Task 4/25] Current/Best: 16.94/ 19.17 GFLOPS | Progress: (8/20) | 8.90 s
[Task 4/25] Current/Best: 15.21/ 19.17 GFLOPS | Progress: (12/20) | 10.37 s
[Task 4/25] Current/Best: 16.40/ 19.17 GFLOPS | Progress: (16/20) | 12.18 s
[Task 4/25] Current/Best: 22.77/ 22.77 GFLOPS | Progress: (20/20) | 14.81 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 15.13/ 15.13 GFLOPS | Progress: (4/20) | 3.20 s
[Task 5/25] Current/Best: 1.81/ 17.06 GFLOPS | Progress: (8/20) | 5.49 s
[Task 5/25] Current/Best: 11.59/ 17.25 GFLOPS | Progress: (12/20) | 7.67 s
[Task 5/25] Current/Best: 12.13/ 19.54 GFLOPS | Progress: (16/20) | 9.59 s
[Task 5/25] Current/Best: 13.05/ 19.54 GFLOPS | Progress: (20/20) | 11.18 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.55/ 14.03 GFLOPS | Progress: (4/20) | 4.13 s
[Task 6/25] Current/Best: 24.52/ 24.52 GFLOPS | Progress: (8/20) | 6.25 s
[Task 6/25] Current/Best: 11.46/ 24.52 GFLOPS | Progress: (12/20) | 8.57 s
[Task 6/25] Current/Best: 10.11/ 24.52 GFLOPS | Progress: (16/20) | 11.92 s
[Task 6/25] Current/Best: 10.68/ 24.52 GFLOPS | Progress: (20/20) | 15.04 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.06/ 16.82 GFLOPS | Progress: (4/20) | 3.28 s
[Task 7/25] Current/Best: 18.93/ 18.93 GFLOPS | Progress: (8/20) | 5.46 s
[Task 7/25] Current/Best: 15.20/ 19.41 GFLOPS | Progress: (12/20) | 6.98 s
[Task 7/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (16/20) | 8.73 s
[Task 7/25] Current/Best: 20.45/ 20.45 GFLOPS | Progress: (20/20) | 11.18 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 15.31/ 15.31 GFLOPS | Progress: (4/20) | 4.14 s
[Task 8/25] Current/Best: 13.96/ 15.34 GFLOPS | Progress: (8/20) | 7.12 s
[Task 8/25] Current/Best: 20.19/ 20.19 GFLOPS | Progress: (12/20) | 16.62 s
[Task 8/25] Current/Best: 10.04/ 20.19 GFLOPS | Progress: (16/20) | 19.53 s
[Task 8/25] Current/Best: 23.18/ 23.77 GFLOPS | Progress: (20/20) | 21.10 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (4/20) | 5.04 s
[Task 9/25] Current/Best: 17.44/ 17.91 GFLOPS | Progress: (8/20) | 15.91 s
[Task 9/25] Current/Best: 8.41/ 18.19 GFLOPS | Progress: (12/20) | 20.54 s
[Task 9/25] Current/Best: 20.46/ 23.32 GFLOPS | Progress: (16/20) | 22.23 s
[Task 9/25] Current/Best: 9.21/ 23.32 GFLOPS | Progress: (20/20) | 23.76 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.53/ 18.53 GFLOPS | Progress: (4/20) | 3.60 s
[Task 10/25] Current/Best: 12.16/ 18.53 GFLOPS | Progress: (8/20) | 5.45 s
[Task 10/25] Current/Best: 14.30/ 18.53 GFLOPS | Progress: (12/20) | 7.43 s
[Task 10/25] Current/Best: 13.82/ 18.53 GFLOPS | Progress: (16/20) | 11.15 s
[Task 10/25] Current/Best: 6.42/ 18.53 GFLOPS | Progress: (20/20
) | 12.78 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 16.54/ 23.87 GFLOPS | Progress: (4/20) | 3.34 s
[Task 11/25] Current/Best: 1.63/ 23.87 GFLOPS | Progress: (8/20) | 8.57 s
[Task 11/25] Current/Best: 12.84/ 23.87 GFLOPS | Progress: (12/20) | 10.76 s
[Task 11/25] Current/Best: 12.36/ 24.49 GFLOPS | Progress: (16/20) | 12.91 s
[Task 11/25] Current/Best: 8.10/ 24.49 GFLOPS | Progress: (20/20) | 15.01 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.93/ 16.73 GFLOPS | Progress: (4/20) | 5.21 s
[Task 12/25] Current/Best: 16.11/ 16.73 GFLOPS | Progress: (8/20) | 7.51 s
[Task 12/25] Current/Best: 13.95/ 18.54 GFLOPS | Progress: (12/20) | 13.59 s
[Task 12/25] Current/Best: 15.27/ 18.54 GFLOPS | Progress: (16/20) | 16.55 s
[Task 12/25] Current/Best: 21.75/ 22.37 GFLOPS | Progress: (20/20) | 19.82 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 10.81/ 19.42 GFLOPS | Progress: (4/20) | 4.05 s
[Task 13/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (8/20) | 6.87 s
[Task 13/25] Current/Best: 21.58/ 21.58 GFLOPS | Progress: (12/20) | 8.89 s
[Task 13/25] Current/Best: 10.33/ 21.58 GFLOPS | Progress: (16/20) | 11.15 s
[Task 13/25] Current/Best: 6.72/ 22.03 GFLOPS | Progress: (20/20) | 15.50 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 17.24/ 17.24 GFLOPS | Progress: (4/20) | 3.53 s
[Task 14/25] Current/Best: 13.44/ 19.52 GFLOPS | Progress: (8/20) | 5.88 s
[Task 14/25] Current/Best: 22.43/ 22.43 GFLOPS | Progress: (12/20) | 7.32 s
[Task 14/25] Current/Best: 15.30/ 22.43 GFLOPS | Progress: (16/20) | 9.54 s Done.
-
[Task 14/25] Current/Best: 12.83/ 22.43 GFLOPS | Progress: (20/20) | 11.63 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 3.23/ 12.53 GFLOPS | Progress: (4/20) | 4.00 s
[Task 15/25] Current/Best: 15.32/ 15.32 GFLOPS | Progress: (8/20) | 6.90 s
[Task 15/25] Current/Best: 18.24/ 19.96 GFLOPS | Progress: (12/20) | 8.47 s
[Task 15/25] Current/Best: 16.60/ 19.96 GFLOPS | Progress: (16/20) | 9.93 s
[Task 15/25] Current/Best: 16.62/ 19.96 GFLOPS | Progress: (20/20) | 13.13 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 5.27/ 17.25 GFLOPS | Progress: (4/20) | 2.87 s
[Task 16/25] Current/Best: 10.06/ 17.25 GFLOPS | Progress: (8/20) | 4.66 s
[Task 16/25] Current/Best: 3.23/ 20.76 GFLOPS | Progress: (12/20) | 6.83 s
[Task 16/25] Current/Best: 11.98/ 20.76 GFLOPS | Progress: (16/20) |
9.64 s
[Task 16/25] Current/Best: 18.15/ 20.76 GFLOPS | Progress: (20/20) | 11.30 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 10.33/ 18.95 GFLOPS | Progress: (4/20) | 3.84 s
[Task 17/25] Current/Best: 22.45/ 22.45 GFLOPS | Progress: (8/20) | 5.88 s
[Task 17/25] Current/Best: 11.49/ 22.45 GFLOPS | Progress: (12/20) | 8.23 s
[Task 17/25] Current/Best: 22.81/ 24.35 GFLOPS | Progress: (16/20) | 9.68 s
[Task 17/25] Current/Best: 13.40/ 24.35 GFLOPS | Progress: (20/20) | 12.65 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.82/ 18.82 GFLOPS | Progress: (4/20) | 4.73 s
[Task 18/25] Current/Best: 18.57/ 19.04 GFLOPS | Progress: (8/20) | 6.46 s
[Task 18/25] Current/Best: 1.64/ 19.04 GFLOPS | Progress: (12/20) | 11.95 s
[Task 18/25] Current/Best: 15.31/ 19.04 GFLOPS | Progress: (16/20) | 14.99 s
[Task 18/25] Current/Best: 11.90/ 20.78 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: 6.11/ 19.29 GFLOPS | Progress: (4/20) | 4.71 s
[Task 19/25] Current/Best: 14.98/ 19.29 GFLOPS | Progress: (8/20) | 9.49 s
[Task 19/25] Current/Best: 7.69/ 20.24 GFLOPS | Progress: (12/20) | 12.13 s
[Task 19/25] Current/Best: 18.67/ 21.76 GFLOPS | Progress: (16/20) | 14.67 s
[Task 19/25] Current/Best: 12.64/ 21.76 GFLOPS | Progress: (20/20) | 16.75 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 19.74/ 19.74 GFLOPS | Progress: (4/20) | 3.11 s
[Task 20/25] Current/Best: 11.79/ 19.74 GFLOPS | Progress: (8/20) | 6.01 s
[Task 20/25] Current/Best: 9.82/ 19.74 GFLOPS | Progress: (12/20) | 9.58 s
[Task 20/25] Current/Best: 21.46/ 21.46 GFLOPS | Progress: (16/20) | 11.82 s Done.
-
[Task 20/25] Current/Best: 8.23/ 21.46 GFLOPS | Progress: (20/20) | 17.35 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 7.07/ 19.30 GFLOPS | Progress: (4/20) | 3.26 s
[Task 21/25] Current/Best: 13.75/ 19.30 GFLOPS | Progress: (8/20) | 4.71 s
[Task 21/25] Current/Best: 14.50/ 19.30 GFLOPS | Progress: (12/20) | 7.42 s
[Task 21/25] Current/Best: 12.20/ 19.30 GFLOPS | Progress: (16/20) | 8.75 s
[Task 21/25] Current/Best: 17.74/ 19.30 GFLOPS | Progress: (20/20) | 12.09 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 11.44/ 18.33 GFLOPS | Progress: (4/20) | 4.45 s
[Task 22/25] Current/Best: 7.88/ 18.33 GFLOPS | Progress: (8/20) | 7.42 s
[Task 22/25] Current/Best: 9.74/ 19.28 GFLOPS | Progress: (12/20) | 9.47 s
[Task 22/25] Current/Best: 6.68/ 21.50 GFLOPS | Progress: (16/20) | 11.50 s
[Task 22/25] Current/Best: 10.50/ 21.50 GFLOPS | Progress: (20/20) |
13.62 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 7.37/ 18.20 GFLOPS | Progress: (4/20) | 4.90 s
[Task 23/25] Current/Best: 7.54/ 19.88 GFLOPS | Progress: (8/20) | 13.70 s
[Task 23/25] Current/Best: 6.40/ 19.88 GFLOPS | Progress: (12/20) | 18.33 s
[Task 23/25] Current/Best: 21.34/ 24.75 GFLOPS | Progress: (16/20) | 21.37 s
[Task 23/25] Current/Best: 10.16/ 24.75 GFLOPS | Progress: (20/20) | 25.36 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 11.25/ 11.25 GFLOPS | Progress: (4/20) | 11.94 s
[Task 24/25] Current/Best: 3.91/ 11.25 GFLOPS | Progress: (8/20) | 22.61 s
[Task 24/25] Current/Best: 3.97/ 11.25 GFLOPS | Progress: (12/20) | 33.32 s
[Task 24/25] Current/Best: 10.82/ 11.25 GFLOPS | Progress: (16/20) | 42.08 s
[Task 24/25] Current/Best: 0.00/ 11.25 GFLOPS | Progress: (20/20) | 52.13 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 11.22/ 21.62 GFLOPS | Progress: (4/20) | 6.50 s
[Task 1/25] Current/Best: 23.21/ 23.60 GFLOPS | Progress: (8/20) | 10.39 s
[Task 1/25] Current/Best: 12.87/ 23.60 GFLOPS | Progress: (12/20) | 12.18 s
[Task 1/25] Current/Best: 23.26/ 23.60 GFLOPS | Progress: (16/20) | 15.27 s
[Task 1/25] Current/Best: 6.41/ 23.60 GFLOPS | Progress: (20/20) | 17.93 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.93 s
[Task 2/25] Current/Best: 8.59/ 18.20 GFLOPS | Progress: (8/20) | 4.26 s
[Task 2/25] Current/Best: 3.66/ 18.20 GFLOPS | Progress: (12/20) | 6.34 s
[Task 2/25] Current/Best: 14.05/ 18.20 GFLOPS | Progress: (16/20) | 7.97 s
[Task 2/25] Current/Best: 6.28/ 19.32 GFLOPS | Progress: (20/20) | 9.04 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 16.47/ 16.47 GFLOPS | Progress: (4/20) | 4.07 s
[Task 3/25] Current/Best: 6.95/ 19.31 GFLOPS | Progress: (8/20) | 6.87 s
[Task 3/25] Current/Best: 9.30/ 23.37 GFLOPS | Progress: (12/20) | 8.78 s
[Task 3/25] Current/Best: 12.47/ 23.37 GFLOPS | Progress: (16/20) | 12.52 s
[Task 3/25] Current/Best: 18.98/ 23.37 GFLOPS | Progress: (20/20) | 14.23 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (4/20) | 3.68 s
[Task 4/25] Current/Best: 8.19/ 17.47 GFLOPS | Progress: (8/20) | 5.63 s
[Task 4/25] Current/Best: 12.03/ 17.47 GFLOPS | Progress: (12/20) | 7.47 s
[Task 4/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (16/20) | 9.56 s
[Task 4/25] Current/Best: 5.79/ 20.48 GFLOPS | Progress: (20/20) | 12.29 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 3.39/ 15.86 GFLOPS | Progress: (4/20) | 3.44 s
[Task 5/25] Current/Best: 5.61/ 17.68 GFLOPS | Progress: (8/20) | 5.22 s
[Task 5/25] Current/Best: 19.75/ 19.75 GFLOPS | Progress: (12/20) | 7.22 s
[Task 5/25] Current/Best: 9.76/ 22.77 GFLOPS | Progress: (16/20) | 8.92 s
[Task 5/25] Current/Best: 14.36/ 22.77 GFLOPS | Progress: (20/20) | 10.75 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (4/20) | 4.49 s
[Task 6/25] Current/Best: 2.96/ 18.12 GFLOPS | Progress: (8/20) | 6.95 s
[Task 6/25] Current/Best: 15.87/ 18.12 GFLOPS | Progress: (12/20) | 8.92 s
[Task 6/25] Current/Best: 17.54/ 18.12 GFLOPS | Progress: (16/20) | 12.56 s
[Task 6/25] Current/Best: 13.25/ 18.37 GFLOPS | Progress: (20/20) | 15.01 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 4.85/ 17.31 GFLOPS | Progress: (4/20) | 3.79 s
[Task 7/25] Current/Best: 17.47/ 22.81 GFLOPS | Progress: (8/20) | 5.56 s
[Task 7/25] Current/Best: 8.82/ 22.81 GFLOPS | Progress: (12/20) | 7.55 s
[Task 7/25] Current/Best: 11.39/ 22.81 GFLOPS | Progress: (16/20) | 10.21 s
[Task 7/25] Current/Best: 11.22/ 22.81 GFLOPS | Progress: (20/20) | 12.32 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 17.24/ 17.24 GFLOPS | Progress: (4/20) | 8.58 s
[Task 8/25] Current/Best: 13.44/ 17.24 GFLOPS | Progress: (8/20) | 12.75 s
[Task 8/25] Current/Best: 5.21/ 17.24 GFLOPS | Progress: (12/20) | 20.28 s
[Task 8/25] Current/Best: 13.37/ 17.24 GFLOPS | Progress: (16/20) | 24.24 s
[Task 8/25] Current/Best: 4.60/ 17.24 GFLOPS | Progress: (20/20) | 30.37 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 10.24/ 16.68 GFLOPS | Progress: (4/20) | 5.43 s
[Task 9/25] Current/Best: 12.12/ 16.68 GFLOPS | Progress: (8/20) | 12.74 s
[Task 9/25] Current/Best: 6.55/ 17.67 GFLOPS | Progress: (12/20) | 20.25 s
[Task 9/25] Current/Best: 19.25/ 19.25 GFLOPS | Progress: (16/20) | 21.83 s
[Task 9/25] Current/Best: 9.02/ 19.25 GFLOPS | Progress: (20/20) | 29.69 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 4.61/ 19.17 GFLOPS | Progress: (4/20) | 3.28 s
[Task 10/25] Current/Best: 11.97/ 19.17 GFLOPS | Progress: (8/20) | 4.90 s
[Task 10/25] Current/Best: 3.89/ 19.17 GFLOPS | Progress: (12/20) | 6.56 s
[Task 10/25] Current/Best: 15.43/ 19.17 GFLOPS | Progress: (16/20) | 8.68 s
[Task 10/25] Current/Best: 14.10/ 19.17 GFLOPS | Progress: (20/20) | 10.67 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.82/ 20.78 GFLOPS | Progress: (4/20) | 3.26 s
[Task 11/25] Current/Best: 9.63/ 20.78 GFLOPS | Progress: (8/20) | 5.09 s
[Task 11/25] Current/Best: 11.22/ 20.78 GFLOPS | Progress: (12/20) | 7.45 s
[Task 11/25] Current/Best: 11.70/ 20.78 GFLOPS | Progress: (16/20) | 9.81 s
[Task 11/25] Current/Best: 18.41/ 20.78 GFLOPS | Progress: (20/20) | 12.23 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 8.11/ 17.26 GFLOPS | Progress: (4/20) | 7.81 s
[Task 12/25] Current/Best: 10.94/ 17.26 GFLOPS | Progress: (8/20) | 11.83 s
[Task 12/25] Current/Best: 14.37/ 18.12 GFLOPS | Progress: (12/20) | 13.93 s
[Task 12/25] Current/Best: 14.86/ 18.12 GFLOPS | Progress: (16/20) | 15.98 s
[Task 12/25] Current/Best: 19.75/ 19.75 GFLOPS | Progress: (20/20) | 17.49 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 13.99/ 18.34 GFLOPS | Progress: (4/20) | 5.39 s
[Task 13/25] Current/Best: 21.14/ 21.14 GFLOPS | Progress: (8/20) | 7.34 s
[Task 13/25] Current/Best: 12.04/ 21.14 GFLOPS | Progress: (12/20) | 10.56 s
[Task 13/25] Current/Best: 8.28/ 21.14 GFLOPS | Progress: (16/20) | 12.97 s
[Task 13/25] Current/Best: 13.41/ 21.47 GFLOPS | Progress: (20/20) | 14.75 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 16.97/ 16.97 GFLOPS | Progress: (4/20) | 8.40 s
[Task 14/25] Current/Best: 1.60/ 16.97 GFLOPS | Progress: (8/20) | 12.43 s
[Task 14/25] Current/Best: 12.03/ 16.97 GFLOPS | Progress: (12/20) | 16.29 s
[Task 14/25] Current/Best: 10.95/ 18.67 GFLOPS | Progress: (16/20) | 19.31 s
[Task 14/25] Current/Best: 10.99/ 19.01 GFLOPS | Progress: (20/20) | 23.86 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 19.78/ 19.78 GFLOPS | Progress: (4/20) | 3.49 s Done.
+
[Task 15/25] Current/Best: 13.57/ 19.78 GFLOPS | Progress: (8/20) | 5.41 s
[Task 15/25] Current/Best: 5.12/ 19.78 GFLOPS | Progress: (12/20) | 9.85 s
[Task 15/25] Current/Best: 6.69/ 19.78 GFLOPS | Progress: (16/20) | 12.27 s
[Task 15/25] Current/Best: 11.89/ 19.78 GFLOPS | Progress: (20/20) | 14.96 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.81/ 19.81 GFLOPS | Progress: (4/20) | 2.76 s
[Task 16/25] Current/Best: 18.30/ 19.81 GFLOPS | Progress: (8/20) | 4.44 s
[Task 16/25] Current/Best: 14.87/ 19.81 GFLOPS | Progress: (12/20) | 5.82 s
[Task 16/25] Current/Best: 14.05/ 19.81 GFLOPS | Progress: (16/20) | 7.86 s
[Task 16/25] Current/Best: 11.20/ 19.81 GFLOPS | Progress: (20/20) | 10.12 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 21.82/ 21.82 GFLOPS | Progress: (4/20) | 4.32 s
[Task 17/25] Current/Best: 21.09/ 21.82 GFLOPS | Progress: (8/20) | 7.82 s
[Task 17/25] Current/Best: 20.57/ 21.82 GFLOPS | Progress: (12/20) | 9.96 s
[Task 17/25] Current/Best: 15.28/ 21.82 GFLOPS | Progress: (16/20) | 12.67 s
[Task 17/25] Current/Best: 13.60/ 21.82 GFLOPS | Progress: (20/20) | 16.15 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 13.95/ 16.75 GFLOPS | Progress: (4/20) | 5.93 s
[Task 18/25] Current/Best: 20.47/ 20.47 GFLOPS | Progress: (8/20) | 9.54 s
[Task 18/25] Current/Best: 15.44/ 20.47 GFLOPS | Progress: (12/20) | 11.25 s
[Task 18/25] Current/Best: 10.49/ 20.79 GFLOPS | Progress: (16/20) | 13.06 s
[Task 18/25] Current/Best: 20.70/ 20.79 GFLOPS | Progress: (20/20) | 15.18 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 16.31/ 16.31 GFLOPS | Progress: (4/20) | 8.42 s
[Task 19/25] Current/Best: 15.57/ 19.69 GFLOPS | Progress: (8/20) | 10.44 s
[Task 19/25] Current/Best: 21.87/ 21.87 GFLOPS | Progress: (12/20) | 12.79 s
[Task 19/25] Current/Best: 8.72/ 21.87 GFLOPS | Progress: (16/20) | 18.90 s
[Task 19/25] Current/Best: 10.51/ 21.87 GFLOPS | Progress: (20/20) | 22.70 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 3.09/ 15.55 GFLOPS | Progress: (4/20) | 3.88 s
[Task 20/25] Current/Best: 11.30/ 15.55 GFLOPS | Progress: (8/20) | 6.61 s
[Task 20/25] Current/Best: 19.19/ 19.19 GFLOPS | Progress: (12/20) | 9.15 s
[Task 20/25] Current/Best: 15.03/ 19.19 GFLOPS | Progress: (16/20) | 11.82 s
[Task 20/25] Current/Best: 7.74/ 19.19 GFLOPS | Progress: (20/20) | 16.42 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 10.48/ 22.64 GFLOPS | Progress: (4/20) | 3.40 s
[Task 21/25] Current/Best: 12.03/ 22.64 GFLOPS | Progress: (8/20) | 6.82 s Done.
+
[Task 21/25] Current/Best: 9.10/ 22.64 GFLOPS | Progress: (12/20) | 14.05 s
[Task 21/25] Current/Best: 9.51/ 22.64 GFLOPS | Progress: (16/20) | 15.48 s
[Task 21/25] Current/Best: 8.77/ 22.64 GFLOPS | Progress: (20/20) | 17.46 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 9.98/ 18.24 GFLOPS | Progress: (4/20) | 5.19 s
[Task 22/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (8/20) | 6.47 s
[Task 22/25] Current/Best: 10.38/ 20.56 GFLOPS | Progress: (12/20) | 8.09 s
[Task 22/25] Current/Best: 7.39/ 20.56 GFLOPS | Progress: (16/20) | 9.98 s
[Task 22/25] Current/Best: 2.69/ 20.56 GFLOPS | Progress: (20/20) | 13.14 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 9.39/ 12.20 GFLOPS | Progress: (4/20) | 4.69 s
[Task 23/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (8/20) | 7.82 s
[Task 23/25] Current/Best: 19.82/ 20.61 GFLOPS | Progress: (12/20) | 10.42 s
[Task 23/25] Current/Best: 19.25/ 20.61 GFLOPS | Progress: (16/20) | 12.68 s
[Task 23/25] Current/Best: 9.25/ 20.61 GFLOPS | Progress: (20/20) | 16.29 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/20) | 11.57 s
[Task 24/25] Current/Best: 6.13/ 6.13 GFLOPS | Progress: (8/20) | 23.59 s
[Task 24/25] Current/Best: 3.82/ 6.13 GFLOPS | Progress: (12/20) | 34.31 s
[Task 24/25] Current/Best: 9.87/ 9.87 GFLOPS | Progress: (16/20) | 44.81 s
[Task 24/25] Current/Best: 2.43/ 9.87 GFLOPS | Progress: (20/20) | 55.53 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 25/25] Current/Best: 9.23/ 9.23 GFLOPS | Progress: (4/20) | 5.45 s
[Task 25/25] Current/Best: 9.99/ 9.99 GFLOPS | Progress: (8/20) | 16.16 s
[Task 25/25] Current/Best: 3.61/ 9.99 GFLOPS | Progress: (12/20) | 26.81 s
[Task 25/25] Current/Best: 8.87/ 9.99 GFLOPS | Progress: (16/20) | 34.90 s
[Task 25/25] Current/Best: 1.53/ 9.99 GFLOPS | Progress: (20/20) | 45.63 s
+
[Task 25/25] Current/Best: 7.48/ 9.23 GFLOPS | Progress: (4/20) | 3.89 s
[Task 25/25] Current/Best: 1.52/ 9.23 GFLOPS | Progress: (8/20) | 6.76 s
[Task 25/25] Current/Best: 4.65/ 9.23 GFLOPS | Progress: (12/20) | 17.47 s
[Task 25/25] Current/Best: 4.63/ 9.23 GFLOPS | Progress: (16/20) | 19.35 s
[Task 25/25] Current/Best: 8.63/ 9.23 GFLOPS | Progress: (20/20) | 20.68 s
@@ -731,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 374.4422222999947, 'median': 374.11153374998776, 'std': 1.305143620401463}
- unoptimized: {'mean': 449.25081586999113, 'median': 449.23343220000334, 'std': 0.34440191044046886}
+ optimized: {'mean': 422.1448080200116, 'median': 421.7878768499759, 'std': 1.9461276369374716}
+ unoptimized: {'mean': 513.4801238399996, 'median': 513.4811045999868, 'std': 1.5907666360712405}
@@ -755,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 37.054 seconds)
+ **Total running time of the script:** ( 10 minutes 56.138 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 8ebd5a74e2..ad7fd6b3b9 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
- 1.181e-07 secs/op
+ 1.281e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index a557e23196..8c0daea4df 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, 0x23482350)), stage(b, placeholder(b, 0x1b72b350)), 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 [...]
+ [stage(a, placeholder(a, 0x2710f9a0)), stage(b, placeholder(b, 0x9c4f140)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index d9c06b51c9..e7e622ed90 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
=================
-**13:52.136** total execution time for **tutorial** files:
+**14:24.892** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:37.054 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:56.138 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:27.133 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:15.678 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:56.874 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.332 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.953 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:37.353 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:15.611 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.478 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.732 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.957 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.617 | 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``) | 00:00.155 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.183 | 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_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 |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.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 6f2f1e859f..bc88311651 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000005
- naive: 0.000010
+ Numpy running time: 0.000008
+ naive: 0.000007
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000009
+ parallel: 0.000006
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 4.6821400019325665e-06 1.0
- naive 9.787e-06 2.090283501979947
- parallel 9.2054e-06 1.9660667977037092
- vector 2.4662400000000003e-05 5.2673350198457385
+ numpy 7.697099999859346e-06 1.0
+ naive 6.6545e-06 0.8645463876163233
+ parallel 5.9999e-06 0.7795013706603318
+ vector 2.45069e-05 3.1839134219963143
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.014140
+ Numpy running time: 0.018070
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.161846
+ none: 3.205048
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.281489
+ blocking: 0.301051
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.321669
+ vectorization: 0.339003
@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: 0.109547
+ loop permutation: 0.117476
@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: 0.103445
+ array packing: 0.109966
@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: 0.095541
+ block caching: 0.110756
@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: 0.127192
+ parallelization: 0.146841
@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 3.161846498 1.0
- blocking 0.2814894921 0.08902693166099425
- vectorization 0.3216692815 0.10173462933873269
- loop permutation 0.10954691840000001 0.03464650117242978
- array packing 0.1034450785 0.032716666848132354
- block caching 0.0955409231 0.03021681259998979
- parallelization 0.1271916455 0.04022701468286143
+ none 3.205048199 1.0
+ blocking 0.3010507878 0.09393019047074867
+ vectorization 0.33900296360000004 0.10577156490369524
+ loop permutation 0.11747578510000001 0.03665335988914406
+ array packing 0.1099656729 0.03431014639165494
+ block caching 0.11075600249999999 0.03455673538218761
+ parallelization 0.14684089039999998 0.04581550144731535
diff --git a/docs/commit_hash b/docs/commit_hash
index b005bca29e..95e6dbde1d 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-8c30bda738eb0b07c0457b6ee651f3f32857903b
+72c60ad78a4cd9ca055f567ffd762462a2b85428
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index e132ff3647..3f4aa6793b 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 9.497 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.320 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 f2243608f5..aa7352db94 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 897ms/step
+1/1 [==============================] - 1s 898ms/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 4164c7842b..58a905907f 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.zip373cb7f9-7286-4191-b489-20f6ef85a8b5 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.zip30a3716f-a568-48cd-8d26-7c74d34e71e5 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 81c7cb3576..a382a07974 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,14 +448,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 43.4MB/s]
- 25%|##5 | 10.5M/41.5M [00:00<00:00, 38.3MB/s]
- 34%|###3 | 14.1M/41.5M [00:00<00:00, 36.1MB/s]
- 42%|####2 | 17.5M/41.5M [00:00<00:00, 32.0MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.5MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 40.4MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 42.1MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 39.4MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 44.7MB/s]
+ 26%|##5 | 10.6M/41.5M [00:00<00:00, 40.7MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 30.1MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 38.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 47.3MB/s]
+ 94%|#########3| 39.0M/41.5M [00:00<00:00, 53.9MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 45.6MB/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 fdbd7a4699..6d92908304 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,11 +431,13 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 78.8MB/s]
- 45%|####5 | 20.3M/44.7M [00:00<00:00, 107MB/s]
- 71%|####### | 31.7M/44.7M [00:00<00:00, 101MB/s]
- 93%|#########2| 41.4M/44.7M [00:00<00:00, 96.8MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 102MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 43.7MB/s]
+ 32%|###2 | 14.3M/44.7M [00:00<00:00, 44.2MB/s]
+ 41%|####1 | 18.5M/44.7M [00:00<00:00, 43.9MB/s]
+ 54%|#####3 | 24.0M/44.7M [00:00<00:00, 48.0MB/s]
+ 72%|#######1 | 32.0M/44.7M [00:00<00:00, 52.8MB/s]
+ 90%|########9 | 40.0M/44.7M [00:00<00:00, 47.4MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 50.4MB/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 b6c24a2fb2..0a81b9e59e 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 6.876 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.717 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 062b95c44c..fe2b394011 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:30.501</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:42.135</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:09.497</p></td>
+<td><p>01:11.320</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:06.876</p></td>
+<td><p>01:09.717</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>00:44.418</p></td>
+<td><p>00:44.703</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>00:32.418</p></td>
+<td><p>00:32.266</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>00:27.771</p></td>
+<td><p>00:29.669</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>00:24.917</p></td>
+<td><p>00:26.046</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="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>00:23.707</p></td>
+<td><p>00:25.537</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>00:21.395</p></td>
+<td><p>00:22.783</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:17.206</p></td>
+<td><p>00:17.722</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>00:02.295</p></td>
+<td><p>00:02.374</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 f6ea813169..874839b844 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)
- 14.3773 14.2811 14.8635 13.9957 0.3353
+ 15.8386 15.8180 15.9869 15.7274 0.0865
</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 88ff4bd998..72c634e2b3 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,29 +453,22 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 4%|3 | 6.30M/170M [00:00<00:04, 36.0MB/s]
- 6%|5 | 9.74M/170M [00:00<00:05, 33.3MB/s]
- 8%|8 | 14.3M/170M [00:00<00:04, 38.6MB/s]
- 11%|# | 18.1M/170M [00:00<00:04, 38.7MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:03, 45.1MB/s]
- 18%|#7 | 30.3M/170M [00:00<00:02, 49.6MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 60.0MB/s]
- 27%|##7 | 46.3M/170M [00:01<00:02, 52.9MB/s]
- 31%|###1 | 52.9M/170M [00:01<00:02, 57.2MB/s]
- 37%|###6 | 62.3M/170M [00:01<00:01, 64.3MB/s]
- 40%|#### | 68.5M/170M [00:01<00:01, 62.3MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 72.9MB/s]
- 51%|#####1 | 87.0M/170M [00:01<00:01, 67.3MB/s]
- 56%|#####5 | 94.3M/170M [00:01<00:01, 59.5MB/s]
- 59%|#####8 | 100M/170M [00:01<00:01, 49.0MB/s]
- 66%|######5 | 112M/170M [00:02<00:00, 65.4MB/s]
- 71%|####### | 120M/170M [00:02<00:00, 67.2MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 61.8MB/s]
- 79%|#######9 | 134M/170M [00:02<00:00, 59.2MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 66.1MB/s]
- 94%|#########4| 160M/170M [00:02<00:00, 83.9MB/s]
- 99%|#########9| 168M/170M [00:02<00:00, 73.2MB/s]
-100%|##########| 170M/170M [00:02<00:00, 61.5MB/s]
+ 5%|4 | 8.16M/170M [00:00<00:01, 85.6MB/s]
+ 10%|9 | 16.3M/170M [00:00<00:02, 70.3MB/s]
+ 18%|#8 | 30.6M/170M [00:00<00:01, 103MB/s]
+ 25%|##5 | 42.6M/170M [00:00<00:01, 111MB/s]
+ 32%|###1 | 53.5M/170M [00:00<00:01, 110MB/s]
+ 38%|###7 | 64.3M/170M [00:00<00:01, 97.3MB/s]
+ 45%|####4 | 75.8M/170M [00:00<00:00, 104MB/s]
+ 52%|#####1 | 88.0M/170M [00:00<00:00, 102MB/s]
+ 59%|#####8 | 100M/170M [00:01<00:00, 109MB/s]
+ 65%|######5 | 111M/170M [00:01<00:00, 110MB/s]
+ 72%|#######1 | 122M/170M [00:01<00:00, 97.8MB/s]
+ 78%|#######8 | 133M/170M [00:01<00:00, 104MB/s]
+ 84%|########4 | 143M/170M [00:01<00:00, 93.1MB/s]
+ 90%|########9 | 153M/170M [00:01<00:00, 79.7MB/s]
+ 95%|#########4| 161M/170M [00:01<00:00, 80.7MB/s]
+100%|##########| 170M/170M [00:01<00:00, 95.9MB/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=& [...]
@@ -573,7 +566,7 @@ 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> ( 2 minutes 50.960 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 8.547 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 0efbdc1ca7..bf21d70c97 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,7 +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]
-100%|##########| 13.6M/13.6M [00:00<00:00, 147MB/s]
+ 88%|########7 | 11.9M/13.6M [00:00<00:00, 125MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 119MB/s]
</pre></div>
</div>
</div>
@@ -588,7 +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)
- 82.3219 82.2874 83.2065 82.0870 0.1842
+ 90.3223 90.2844 93.1309 89.9646 0.3712
</pre></div>
</div>
<div class="admonition note">
@@ -627,6 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.532 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 ea46a70be2..a1cbc25747 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)
- 107.5040 107.4360 109.3455 107.1018 0.2973
+ 120.0354 120.0333 121.9064 119.1732 0.3621
</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 16.823 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.960 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 6f349b5dc1..182052d7ae 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 39.758 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.602 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 6799208552..4816253623 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]
- 3%|3 | 4057/132723 [00:00<00:03, 40564.82KB/s]
- 10%|9 | 13146/132723 [00:00<00:01, 70164.58KB/s]
- 17%|#6 | 22555/132723 [00:00<00:01, 81085.21KB/s]
- 24%|##4 | 31887/132723 [00:00<00:01, 85912.88KB/s]
- 30%|### | 40479/132723 [00:00<00:01, 68726.11KB/s]
- 37%|###7 | 49280/132723 [00:00<00:01, 74261.16KB/s]
- 44%|####4 | 58704/132723 [00:00<00:00, 80133.40KB/s]
- 51%|##### | 67044/132723 [00:00<00:00, 79029.05KB/s]
- 58%|#####7 | 76466/132723 [00:00<00:00, 83457.16KB/s]
- 64%|######4 | 84996/132723 [00:01<00:00, 72536.70KB/s]
- 71%|####### | 94016/132723 [00:01<00:00, 77237.83KB/s]
- 77%|#######6 | 102057/132723 [00:01<00:00, 71950.25KB/s]
- 84%|########3 | 111459/132723 [00:01<00:00, 77821.66KB/s]
- 91%|#########1| 120885/132723 [00:01<00:00, 82348.32KB/s]
- 98%|#########8| 130270/132723 [00:01<00:00, 85593.32KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 78465.13KB/s]
+ 4%|3 | 5211/132723 [00:00<00:02, 52093.28KB/s]
+ 10%|9 | 12718/132723 [00:00<00:01, 65605.13KB/s]
+ 15%|#4 | 19279/132723 [00:00<00:02, 52580.85KB/s]
+ 20%|#9 | 26328/132723 [00:00<00:01, 58727.43KB/s]
+ 25%|##4 | 32757/132723 [00:00<00:01, 52957.70KB/s]
+ 29%|##8 | 38282/132723 [00:00<00:01, 52056.09KB/s]
+ 34%|###4 | 45641/132723 [00:00<00:01, 58250.21KB/s]
+ 40%|#### | 53113/132723 [00:00<00:01, 63040.71KB/s]
+ 46%|####5 | 60534/132723 [00:01<00:01, 66320.03KB/s]
+ 51%|#####1 | 68294/132723 [00:01<00:00, 69652.38KB/s]
+ 57%|#####7 | 76171/132723 [00:01<00:00, 72358.61KB/s]
+ 63%|######3 | 84073/132723 [00:01<00:00, 74339.68KB/s]
+ 69%|######9 | 91874/132723 [00:01<00:00, 75433.12KB/s]
+ 75%|#######5 | 99784/132723 [00:01<00:00, 76528.30KB/s]
+ 81%|########1 | 107636/132723 [00:01<00:00, 77122.79KB/s]
+ 87%|########6 | 115372/132723 [00:01<00:00, 73752.62KB/s]
+ 93%|#########2| 122794/132723 [00:01<00:00, 72408.36KB/s]
+ 98%|#########8| 130522/132723 [00:01<00:00, 73813.67KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 67529.47KB/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> ( 2 minutes 43.459 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 58.422 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 d2dd1f827b..733da49170 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:52.991</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:51.084</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>02:50.960</p></td>
+<td><p>03:08.547</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:43.459</p></td>
+<td><p>02:58.422</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>02:16.823</p></td>
+<td><p>02:30.960</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>01:39.758</p></td>
+<td><p>01:42.602</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>00:59.785</p></td>
+<td><p>01:04.532</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>00:34.165</p></td>
+<td><p>00:36.021</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>00:24.257</p></td>
+<td><p>00:25.292</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:23.778</p></td>
+<td><p>00:24.703</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>00:00.006</p></td>
+<td><p>00:00.007</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 8e72917cf1..dcc9bf944f 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.zip7fd70611-97df-460a-987e-4039ce1c77f7 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.zip8c5bc586-cbca-4d15-8a97-a7d74d35ff2e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 84ff6d9fb3..5de26898dc 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.008</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.789</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:39.959</p></td>
+<td><p>00:43.371</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>00:02.127</p></td>
+<td><p>00:02.385</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>00:00.915</p></td>
+<td><p>00:01.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index b5684c783d..086db5d648 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: 6762us [6762us] (46.54%; 46.54%)
-FoldScaleAxis: 7767us [6us] (53.46%; 53.46%)
- FoldConstant: 7761us [1619us] (53.42%; 99.92%)
- InferType: 6142us [6142us] (42.27%; 79.14%)
+InferType: 7131us [7131us] (44.88%; 44.88%)
+FoldScaleAxis: 8757us [22us] (55.12%; 55.12%)
+ FoldConstant: 8734us [1703us] (54.98%; 99.74%)
+ InferType: 7031us [7031us] (44.25%; 80.50%)
</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: 6238us [6238us] (45.07%; 45.07%)
-FoldScaleAxis: 7603us [4us] (54.93%; 54.93%)
- FoldConstant: 7598us [1507us] (54.90%; 99.94%)
- InferType: 6092us [6092us] (44.01%; 80.17%)
+InferType: 6653us [6653us] (45.13%; 45.13%)
+FoldScaleAxis: 8089us [5us] (54.87%; 54.87%)
+ FoldConstant: 8084us [1669us] (54.84%; 99.94%)
+ InferType: 6415us [6415us] (43.51%; 79.35%)
</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 294e49c7ff..e231cd14df 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.145023 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.130718 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 ff964f0dd0..26559fcff4 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: 6.842969 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.118951 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 37109998b2..83dee807b0 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: 0.013832
-Baseline: 3.343903
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017861
+Baseline: 3.252491
</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: 0.272480
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301002
</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: 0.302276
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336036
</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: 0.104893
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114605
</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: 0.099920
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109476
</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: 0.094371
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112047
</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: 0.122287
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146412
</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 42deab54ce..210eb05a10 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.486</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.078</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>00:29.098</p></td>
+<td><p>00:31.714</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>00:01.307</p></td>
+<td><p>00:01.357</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>00:01.081</p></td>
+<td><p>00:01.007</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 bbcbf75c6a..1d0ae0a999 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>08:29.382</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:03.587</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>05:18.071</p></td>
+<td><p>05:37.277</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>01:24.356</p></td>
+<td><p>01:31.794</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:57.802</p></td>
+<td><p>01:02.709</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:28.267</p></td>
+<td><p>00:29.091</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>00:10.818</p></td>
+<td><p>00:11.767</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>00:10.068</p></td>
+<td><p>00:10.949</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 b907e4f093..106e8dc568 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
@@ -504,12 +504,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -517,645 +517,470 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*3136)
- let cse_var_1: int32 = (rc.outer.outer*576)
+ 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" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 49), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 147), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 245), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 343), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 335)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 539), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 637), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 735), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 833), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 678)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 931), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1029), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1127), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1225), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1021)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1421), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1519), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1617), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1715), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1813), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1911), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2009), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2058), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2107), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 1707)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2254), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2303), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2401), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2450), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2499), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2597)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2597), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2646)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 2050)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2695)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2695), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2793)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2793), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2842)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2842), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2891)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2891), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2989)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2989), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3038)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3038), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3087)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 2393)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3185)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3185), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3234)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3234), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3283)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3283), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3381)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3381), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3430)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3430), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3479)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3479), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 2736)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3577)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3577), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3626)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3626), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3675)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3675), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 1)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3773)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3773), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3822)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3822), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3871)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3871), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((threadIdx.x_1 < 42) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + ((floordiv(threadIdx.x_1, 7) + 2)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 3969)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) + 3079)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 4018)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 4018), 63)*49)) + rx.outer.outer) + threadIdx.x_1) + 41)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 49), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 53), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 34)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 151), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 19)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 106), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 155), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 61), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 53), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 833)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 833), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 65), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 882), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 38)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 931)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 931), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 163), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 980), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1029)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1029), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 23)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1078), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 118), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1127)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1127), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 167), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1225)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1225), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 73), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1274), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 122), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1323)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1323), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 57), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1372), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1421)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1421), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 77), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1470), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 42)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 17), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1519)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1519), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 175), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ff.outer.inner: int32, 0, 2) {
- let cse_var_7: int32 = (ff.outer.inner*4)
- let cse_var_6: int32 = (cse_var_7 + 3)
- let cse_var_5: int32 = (cse_var_7 + 2)
- let cse_var_4: int32 = (cse_var_7 + 1)
- let cse_var_3: int32 = ((ff.outer.inner*768) + (rc.outer.inner*96))
- {
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[cse_var_3]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 192)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 384)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((rc.outer.inner*2016) + threadIdx.x)]*kernel.shared_1[(cse_var_3 + 576)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 1)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 193)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 385)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 7)]*kernel.shared_1[(cse_var_3 + 577)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 2)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 194)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 386)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 14)]*kernel.shared_1[(cse_var_3 + 578)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 3)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 195)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 387)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 63)]*kernel.shared_1[(cse_var_3 + 579)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 4)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 196)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 388)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 70)]*kernel.shared_1[(cse_var_3 + 580)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 5)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 197)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 389)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 77)]*kernel.shared_1[(cse_var_3 + 581)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 6)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 198)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 390)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 126)]*kernel.shared_1[(cse_var_3 + 582)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 7)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 199)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 391)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 133)]*kernel.shared_1[(cse_var_3 + 583)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 8)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 200)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 392)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 140)]*kernel.shared_1[(cse_var_3 + 584)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 9)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 201)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 393)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 189)]*kernel.shared_1[(cse_var_3 + 585)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 10)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 202)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 394)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 196)]*kernel.shared_1[(cse_var_3 + 586)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 11)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 203)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 395)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 203)]*kernel.shared_1[(cse_var_3 + 587)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 12)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 204)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 396)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 252)]*kernel.shared_1[(cse_var_3 + 588)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 13)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 205)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 397)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 259)]*kernel.shared_1[(cse_var_3 + 589)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 14)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 206)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 398)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 266)]*kernel.shared_1[(cse_var_3 + 590)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 15)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 207)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 399)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 315)]*kernel.shared_1[(cse_var_3 + 591)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 16)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 208)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 400)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 322)]*kernel.shared_1[(cse_var_3 + 592)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 17)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 209)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 401)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 329)]*kernel.shared_1[(cse_var_3 + 593)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 18)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 210)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 402)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 378)]*kernel.shared_1[(cse_var_3 + 594)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 19)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 211)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 403)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 385)]*kernel.shared_1[(cse_var_3 + 595)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 20)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 212)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 404)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 392)]*kernel.shared_1[(cse_var_3 + 596)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 21)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 213)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 405)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 441)]*kernel.shared_1[(cse_var_3 + 597)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 22)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 214)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 406)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 448)]*kernel.shared_1[(cse_var_3 + 598)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 23)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 215)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 407)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 455)]*kernel.shared_1[(cse_var_3 + 599)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 24)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 216)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 408)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 504)]*kernel.shared_1[(cse_var_3 + 600)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 25)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 217)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 409)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 511)]*kernel.shared_1[(cse_var_3 + 601)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 26)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 218)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 410)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 518)]*kernel.shared_1[(cse_var_3 + 602)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 27)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 219)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 411)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 567)]*kernel.shared_1[(cse_var_3 + 603)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 28)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 220)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 412)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 574)]*kernel.shared_1[(cse_var_3 + 604)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 29)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 221)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 413)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 581)]*kernel.shared_1[(cse_var_3 + 605)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 30)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 222)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 414)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 630)]*kernel.shared_1[(cse_var_3 + 606)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 31)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 223)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 415)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 637)]*kernel.shared_1[(cse_var_3 + 607)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 32)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 224)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 416)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 644)]*kernel.shared_1[(cse_var_3 + 608)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 33)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 225)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 417)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 693)]*kernel.shared_1[(cse_var_3 + 609)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 34)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 226)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 418)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 700)]*kernel.shared_1[(cse_var_3 + 610)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 35)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 227)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 419)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 707)]*kernel.shared_1[(cse_var_3 + 611)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 36)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 228)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 420)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 756)]*kernel.shared_1[(cse_var_3 + 612)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 37)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 229)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 421)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 763)]*kernel.shared_1[(cse_var_3 + 613)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 38)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 230)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 422)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 770)]*kernel.shared_1[(cse_var_3 + 614)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 39)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 231)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 423)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 819)]*kernel.shared_1[(cse_var_3 + 615)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 40)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 232)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 424)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 826)]*kernel.shared_1[(cse_var_3 + 616)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 41)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 233)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 425)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 833)]*kernel.shared_1[(cse_var_3 + 617)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 42)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 234)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 426)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 882)]*kernel.shared_1[(cse_var_3 + 618)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 43)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 235)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 427)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 889)]*kernel.shared_1[(cse_var_3 + 619)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 44)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 236)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 428)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 896)]*kernel.shared_1[(cse_var_3 + 620)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 45)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 237)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 429)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 945)]*kernel.shared_1[(cse_var_3 + 621)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 46)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 238)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 430)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 952)]*kernel.shared_1[(cse_var_3 + 622)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 47)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 239)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 431)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 959)]*kernel.shared_1[(cse_var_3 + 623)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 48)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 240)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 432)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1008)]*kernel.shared_1[(cse_var_3 + 624)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 49)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 241)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 433)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1015)]*kernel.shared_1[(cse_var_3 + 625)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 50)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 242)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 434)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1022)]*kernel.shared_1[(cse_var_3 + 626)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 51)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 243)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 435)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1071)]*kernel.shared_1[(cse_var_3 + 627)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 52)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 244)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 436)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1078)]*kernel.shared_1[(cse_var_3 + 628)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 53)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 245)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 437)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1085)]*kernel.shared_1[(cse_var_3 + 629)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 54)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 246)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 438)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1134)]*kernel.shared_1[(cse_var_3 + 630)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 55)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 247)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 439)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1141)]*kernel.shared_1[(cse_var_3 + 631)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 56)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 248)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 440)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1148)]*kernel.shared_1[(cse_var_3 + 632)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 57)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 249)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 441)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1197)]*kernel.shared_1[(cse_var_3 + 633)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 58)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 250)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 442)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1204)]*kernel.shared_1[(cse_var_3 + 634)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 59)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 251)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 443)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1211)]*kernel.shared_1[(cse_var_3 + 635)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 60)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 252)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 444)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1260)]*kernel.shared_1[(cse_var_3 + 636)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 61)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 253)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 445)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1267)]*kernel.shared_1[(cse_var_3 + 637)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 62)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 254)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 446)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1274)]*kernel.shared_1[(cse_var_3 + 638)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 63)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 255)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 447)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1323)]*kernel.shared_1[(cse_var_3 + 639)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 64)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 256)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 448)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1330)]*kernel.shared_1[(cse_var_3 + 640)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 65)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 257)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 449)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1337)]*kernel.shared_1[(cse_var_3 + 641)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 66)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 258)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 450)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1386)]*kernel.shared_1[(cse_var_3 + 642)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 67)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 259)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 451)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1393)]*kernel.shared_1[(cse_var_3 + 643)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 68)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 260)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 452)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1400)]*kernel.shared_1[(cse_var_3 + 644)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 69)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 261)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 453)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1449)]*kernel.shared_1[(cse_var_3 + 645)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 70)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 262)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 454)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1456)]*kernel.shared_1[(cse_var_3 + 646)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 71)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 263)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 455)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1463)]*kernel.shared_1[(cse_var_3 + 647)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 72)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 264)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 456)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1512)]*kernel.shared_1[(cse_var_3 + 648)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 73)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 265)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 457)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1519)]*kernel.shared_1[(cse_var_3 + 649)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 74)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 266)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 458)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1526)]*kernel.shared_1[(cse_var_3 + 650)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 75)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 267)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 459)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1575)]*kernel.shared_1[(cse_var_3 + 651)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 76)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 268)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 460)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1582)]*kernel.shared_1[(cse_var_3 + 652)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 77)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 269)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 461)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1589)]*kernel.shared_1[(cse_var_3 + 653)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 78)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 270)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 462)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1638)]*kernel.shared_1[(cse_var_3 + 654)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 79)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 271)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 463)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1645)]*kernel.shared_1[(cse_var_3 + 655)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 80)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 272)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 464)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1652)]*kernel.shared_1[(cse_var_3 + 656)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 81)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 273)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 465)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1701)]*kernel.shared_1[(cse_var_3 + 657)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 82)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 274)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 466)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1708)]*kernel.shared_1[(cse_var_3 + 658)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 83)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 275)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 467)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1715)]*kernel.shared_1[(cse_var_3 + 659)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 84)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 276)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 468)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1764)]*kernel.shared_1[(cse_var_3 + 660)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 85)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 277)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 469)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1771)]*kernel.shared_1[(cse_var_3 + 661)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 86)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 278)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 470)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1778)]*kernel.shared_1[(cse_var_3 + 662)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 87)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 279)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 471)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1827)]*kernel.shared_1[(cse_var_3 + 663)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 88)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 280)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 472)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1834)]*kernel.shared_1[(cse_var_3 + 664)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 89)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 281)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 473)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1841)]*kernel.shared_1[(cse_var_3 + 665)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 90)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 282)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 474)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1890)]*kernel.shared_1[(cse_var_3 + 666)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 91)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 283)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 475)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1897)]*kernel.shared_1[(cse_var_3 + 667)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 92)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 284)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 476)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1904)]*kernel.shared_1[(cse_var_3 + 668)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 93)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 285)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 477)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1953)]*kernel.shared_1[(cse_var_3 + 669)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 94)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 286)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 478)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1960)]*kernel.shared_1[(cse_var_3 + 670)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 95)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 287)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 479)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*2016) + threadIdx.x) + 1967)]*kernel.shared_1[(cse_var_3 + 671)]))
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
}
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -1192,7 +1017,7 @@ 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: 0.242 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.349 ms
</pre></div>
</div>
</div>
@@ -1221,36 +1046,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1270,12 +1095,12 @@ 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=49)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1295,10 +1120,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[1536];
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1307,521 +1132,418 @@ extern "C" __global__ void __launch_bounds__(49) default_function_kern
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ 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();
- pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 335)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1021)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1364)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 1707)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2050)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2393)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 2736)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) - 1)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((int)threadIdx.x) < 42) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((int)threadIdx.x)) + rx_outer_outer) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 3136) + ((int)threadIdx.x)) + rx_outer_outer) + 3079)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((int)threadIdx.x) < 7) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 63) * 49)) + rx_outer_outer) + ((int)threadIdx.x)) + 41)] : 0.000000e+00f);
+ 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);
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 49) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 98) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 49) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 53) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 306)];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 151) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 171)];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 106) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 155) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 36)];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 61) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 110) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 53) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 833)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 833) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 65) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 882)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 882) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 342)];
- kernel_shared[(((int)threadIdx.x) + 931)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 931) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 163) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 20) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1029) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 207)];
- kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1078) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 118) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1127) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 167) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1225)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1225) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 73) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1274) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 122) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1323)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1323) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 57) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 28) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1421)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1421) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 77) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1470) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 378)];
- if (((int)threadIdx.x) < 17) {
- kernel_shared[(((int)threadIdx.x) + 1519)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1519) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 175) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ 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);
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[((ff_outer_inner * 768) + (rc_outer_inner * 96))]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 192)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 384)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[((rc_outer_inner * 2016) + ((int)threadIdx.x))] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 576)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 193)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 385)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 7)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 577)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 194)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 386)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 14)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 578)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 195)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 387)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 63)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 579)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 196)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 388)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 70)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 580)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 197)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 389)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 77)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 581)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 198)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 390)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 126)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 582)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 199)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 391)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 133)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 583)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 200)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 392)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 140)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 584)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 201)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 393)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 189)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 585)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 202)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 394)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 196)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 586)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 203)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 395)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 203)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 587)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 204)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 396)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 252)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 588)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 205)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 397)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 259)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 589)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 206)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 398)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 266)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 590)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 207)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 399)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 315)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 591)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 208)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 400)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 322)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 592)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 209)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 401)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 329)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 593)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 210)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 402)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 378)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 594)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 211)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 403)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 385)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 595)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 212)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 404)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 392)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 596)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 213)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 405)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 441)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 597)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 214)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 406)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 448)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 598)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 215)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 407)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 455)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 599)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 24)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 216)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 408)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 504)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 600)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 25)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 217)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 409)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 511)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 601)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 26)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 218)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 410)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 518)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 602)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 27)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 219)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 411)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 567)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 603)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 28)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 220)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 412)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 574)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 604)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 29)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 221)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 413)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 581)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 605)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 30)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 222)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 414)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 630)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 606)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 31)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 223)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 415)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 637)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 607)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 32)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 224)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 416)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 644)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 608)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 33)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 225)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 417)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 693)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 609)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 34)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 226)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 418)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 700)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 610)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 35)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 227)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 419)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 707)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 611)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 36)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 228)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 420)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 756)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 612)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 37)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 229)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 421)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 763)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 613)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 38)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 230)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 422)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 770)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 614)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 39)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 231)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 423)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 819)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 615)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 40)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 232)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 424)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 826)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 616)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 41)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 233)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 425)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 833)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 617)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 42)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 234)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 426)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 882)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 618)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 43)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 235)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 427)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 889)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 619)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 44)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 236)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 428)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 896)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 620)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 45)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 237)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 429)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 945)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 621)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 46)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 238)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 430)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 952)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 622)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 47)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 239)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 431)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 959)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 623)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 48)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 240)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 432)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1008)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 624)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 49)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 241)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 433)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1015)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 625)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 50)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 242)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 434)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1022)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 626)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 51)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 243)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 435)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1071)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 627)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 52)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 244)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 436)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1078)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 628)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 53)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 245)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 437)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1085)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 629)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 54)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 246)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 438)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1134)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 630)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 55)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 247)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 439)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1141)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 631)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 56)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 248)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 440)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1148)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 632)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 57)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 249)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 441)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1197)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 633)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 58)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 250)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 442)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1204)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 634)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 59)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 251)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 443)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1211)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 635)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 60)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 252)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 444)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1260)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 636)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 61)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 253)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 445)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1267)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 637)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 62)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 254)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 446)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1274)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 638)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 63)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 255)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 447)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1323)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 639)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 64)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 256)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 448)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1330)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 640)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 65)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 257)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 449)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1337)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 641)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 66)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 258)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 450)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1386)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 642)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 67)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 259)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 451)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1393)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 643)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 68)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 260)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 452)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1400)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 644)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 69)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 261)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 453)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1449)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 645)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 70)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 262)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 454)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1456)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 646)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 71)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 263)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 455)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1463)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 647)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 72)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 264)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 456)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1512)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 648)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 73)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 265)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 457)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1519)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 649)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 74)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 266)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 458)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1526)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 650)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 75)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 267)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 459)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1575)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 651)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 76)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 268)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 460)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1582)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 652)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 77)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 269)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 461)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1589)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 653)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 78)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 270)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 462)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1638)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 654)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 79)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 271)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 463)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1645)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 655)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 80)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 272)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 464)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1652)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 656)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 81)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 273)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 465)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1701)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 657)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 82)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 274)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 466)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1708)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 658)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 83)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 275)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 467)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1715)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 659)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 84)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 276)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 468)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1764)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 660)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 85)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 277)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 469)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1771)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 661)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 86)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 278)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 470)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1778)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 662)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 87)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 279)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 471)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1827)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 663)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 88)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 280)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 472)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1834)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 664)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 89)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 281)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 473)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1841)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 665)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 90)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 282)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 474)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1890)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 666)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 91)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 283)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 475)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1897)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 667)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 92)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 284)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 476)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1904)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 668)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 93)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 285)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 477)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1953)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 669)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 94)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 286)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 478)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1960)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 670)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 95)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 287)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 479)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((rc_outer_inner * 2016) + ((int)threadIdx.x)) + 1967)] * kernel_shared[(((ff_outer_inner * 768) + (rc_outer_inner * 96)) + 671)]));
- }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -1858,7 +1580,7 @@ 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 18.071 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 37.277 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 5480649af0..fb41dd04c3 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)
- 8.1944 8.1998 8.2010 8.1824 0.0085
+ 8.2201 8.2210 8.2265 8.2129 0.0056
</pre></div>
</div>
</div>
@@ -937,6 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.709 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 c9519a289e..1468ba4196 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)
- 678.5120 676.8529 682.4534 676.2298 2.7986
+ 749.5053 749.3239 750.8476 748.3444 1.0299
</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 24.356 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.794 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 4ed0e5498c..404a7fa2e3 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,78 +632,32 @@ 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_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = (((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*1024)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) 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_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -741,7 +695,7 @@ 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: 1.813 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.557 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 a51db1ce60..3833228210 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.034</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:40.157</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:31.001</p></td>
+<td><p>00:40.122</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>00:00.018</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
@@ -361,11 +361,11 @@
<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>
-<td><p>00:00.004</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>
-<td><p>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 e48f9eace8..800f2919ab 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 7.31/7.31 result: MeasureResult(costs=(0.03165303975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.225941896438599, timestamp=1668547854.2140303) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7446696
-No: 2 GFLOPS: 0.00/7.31 result: Traceback (most recent call last):
+No: 1 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -690,9 +689,9 @@ 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, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3477247
-No: 3 GFLOPS: 193.61/193.61 result: MeasureResult(costs=(0.0011957172093023257,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.501504421234131, timestamp=1668547855.7061899) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7323425
-No: 4 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7991273
+No: 2 GFLOPS: 171.39/171.39 result: MeasureResult(costs=(0.0013507484333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.717359781265259, timestamp=1668547719.3734238) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9753105
+No: 3 GFLOPS: 0.00/171.39 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
@@ -814,8 +813,27 @@ 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, 64, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2573063
-No: 5 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5193914
+No: 4 GFLOPS: 0.00/171.39 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, 32, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8728613
+No: 5 GFLOPS: 11.49/171.39 result: MeasureResult(costs=(0.020140954333333332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.108873128890991, timestamp=1668547728.179477) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 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', 512), ('unroll_explicit', 1)],None,7321709
+No: 6 GFLOPS: 0.00/171.39 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
@@ -937,8 +955,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8214845
-No: 6 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,206850
+No: 7 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1060,8 +1078,9 @@ 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, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,639356
-No: 7 GFLOPS: 0.00/193.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10439317
+No: 8 GFLOPS: 55.85/171.39 result: MeasureResult(costs=(0.0041453146,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.635598659515381, timestamp=1668547729.7172017) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2532256
+No: 9 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1183,9 +1202,10 @@ 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, 2, 8, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4966258
-No: 8 GFLOPS: 423.41/423.41 result: MeasureResult(costs=(0.0005467581366120218,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1858747005462646, timestamp=1668547858.8730369) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3940932
-No: 9 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,698557
+No: 10 GFLOPS: 154.09/171.39 result: MeasureResult(costs=(0.0015023335671641791,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4147913455963135, timestamp=1668547731.5769172) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4743442
+No: 11 GFLOPS: 3.91/171.39 result: MeasureResult(costs=(0.0591835365,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.168834924697876, timestamp=1668547732.7012928) [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,24131
+No: 12 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1307,8 +1327,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4579390
-No: 10 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10035867
+No: 13 GFLOPS: 0.00/171.39 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1430,9 +1450,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9154546
-No: 11 GFLOPS: 2.79/423.41 result: MeasureResult(costs=(0.08296199774999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7744982242584229, timestamp=1668547860.8489847) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,693221
-No: 12 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6746441
+No: 14 GFLOPS: 0.00/171.39 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
@@ -1554,8 +1573,8 @@ 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, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9813377
-No: 13 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9802890
+No: 15 GFLOPS: 0.00/171.39 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
@@ -1677,8 +1696,8 @@ 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, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2347780
-No: 14 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7048687
+No: 16 GFLOPS: 0.00/171.39 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
@@ -1800,8 +1819,8 @@ 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, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7526442
-No: 15 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10228449
+No: 17 GFLOPS: 0.00/171.39 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
@@ -1923,8 +1942,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5744335
-No: 16 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,172090
+No: 18 GFLOPS: 0.00/171.39 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
@@ -2046,11 +2065,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2845590
-No: 17 GFLOPS: 92.76/423.41 result: MeasureResult(costs=(0.002495668804347826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7457647323608398, timestamp=1668547864.3853936) [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1093919
-No: 18 GFLOPS: 47.65/423.41 result: MeasureResult(costs=(0.00485826580952381,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0213398933410645, timestamp=1668547865.0483766) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10117283
-No: 19 GFLOPS: 168.75/423.41 result: MeasureResult(costs=(0.0013718832837837838,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5751590728759766, timestamp=1668547865.678287) [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3545599
-No: 20 GFLOPS: 0.00/423.41 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,573934
+No: 19 GFLOPS: 0.00/171.39 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
@@ -2172,7 +2188,130 @@ 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, 4, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5674667
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10027704
+No: 20 GFLOPS: 0.00/171.39 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, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9899368
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2211,9 +2350,9 @@ 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, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3940932
+[('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9753105
Finish loading 20 records
-Time cost of this operator: 0.000542
+Time cost of this operator: 0.001456
</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 816b5e77c1..b3922be2cd 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -596,10 +596,10 @@ 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 279.7 98.667 (1, 2, 10, 10, 3) 2 1 [279.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.849 1.005 (1, 6, 10, 10) 1 1 [2.849]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.929 0.328 (1, 1, 10, 10, 3) 1 1 [0.929]
-Total_time - 283.478 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.734 (1, 2, 10, 10, 3) 2 1 [310.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.96 (1, 6, 10, 10) 1 1 [3.021]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.306 (1, 1, 10, 10, 3) 1 1 [0.963]
+Total_time - 314.684 - - - - -
</pre></div>
</div>
</div>
@@ -650,10 +650,10 @@ 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 99.438 97.604 (1, 6, 10, 10, 1) 2 1 [99.438]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.586 1.557 (1, 6, 10, 10) 1 1 [1.586]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.855 0.839 (1, 1, 10, 10, 3) 1 1 [0.855]
-Total_time - 101.878 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.9 97.945 (1, 6, 10, 10, 1) 2 1 [134.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.855 1.347 (1, 6, 10, 10) 1 1 [1.855]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.709 (1, 1, 10, 10, 3) 1 1 [0.976]
+Total_time - 137.731 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 9ef12c41e6..dcfcd7de4a 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,8 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 23%|##3 | 816k/3.42M [00:00<00:00, 8.31MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 24.1MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 91.1MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -565,6 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.163 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 1cc95ce52f..7c2b154df4 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpqr12qxcz/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpg5sqjq4r/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpqr12qxcz/images/target contains 8144 images
-/tmp/tmpqr12qxcz/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpg5sqjq4r/images/target contains 8144 images
+/tmp/tmpg5sqjq4r/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 41s - loss: 0.2161 - accuracy: 0.9237 - val_loss: 0.1690 - val_accuracy: 0.9411 - 41s/epoch - 126ms/step
+328/328 - 46s - loss: 0.2142 - accuracy: 0.9258 - val_loss: 0.1235 - val_accuracy: 0.9558 - 46s/epoch - 142ms/step
Epoch 2/3
-328/328 - 38s - loss: 0.0862 - accuracy: 0.9669 - val_loss: 0.1181 - val_accuracy: 0.9630 - 38s/epoch - 115ms/step
+328/328 - 43s - loss: 0.0909 - accuracy: 0.9664 - val_loss: 0.1908 - val_accuracy: 0.9373 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 38s - loss: 0.0669 - accuracy: 0.9753 - val_loss: 0.1275 - val_accuracy: 0.9573 - 38s/epoch - 115ms/step
+328/328 - 43s - loss: 0.0632 - accuracy: 0.9766 - val_loss: 0.1024 - val_accuracy: 0.9645 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7efd81f2ce10>
+<keras.callbacks.History object at 0x7faadce4d090>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 4.321 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 42.678 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 2109517c1e..0f7e7edb59 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:56.960</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:43.592</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:04.321</p></td>
+<td><p>04:42.678</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>00:56.634</p></td>
+<td><p>01:01.163</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:45.287</p></td>
+<td><p>00:48.099</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.281</p></td>
+<td><p>00:07.998</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.435</p></td>
+<td><p>00:03.651</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 6295b9555e..2d62b3053e 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.567</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.182</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>00:29.482</p></td>
+<td><p>00:30.696</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.094</p></td>
+<td><p>00:10.174</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>00:01.985</p></td>
+<td><p>00:01.305</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 99b37eeb80..28a878eb3c 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 0x7efdf0147b90>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fabccc39b00>
</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 d078fef751..31a8e5e211 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.398</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.297</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:02.119</p></td>
+<td><p>00:02.185</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.035</p></td>
+<td><p>00:00.880</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>00:00.535</p></td>
+<td><p>00:00.523</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>00:00.514</p></td>
+<td><p>00:00.501</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>00:00.104</p></td>
+<td><p>00:00.112</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.045</p></td>
+<td><p>00:00.048</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.027</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.018</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 4a35e81d9f..57af7e30db 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/tmpmrfs9xs2/input0.cc'\nsource_filename = \"/tmp/tmpmrfs9xs2/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/tmp_u9dqo0p/input0.cc'\nsource_filename = \"/tmp/tmp_u9dqo0p/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 fbaa2386b0..2ada5744ea 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 34e328c983..a9234129c4 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/8c30bda73/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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 4a01141d52..c36e32a131 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/8c30bda73/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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 ba9490c59a..86345e956a 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/8c30bda73/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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 835f461cef..c42332a65b 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/8c30bda73/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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 05661da9ad..0a14487820 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/8c30bda73/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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 7a8d80cae8..a3f5da3772 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/8c30bda73/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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 7f7d70ae73..679b49554c 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/8c30bda73/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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 804bb398c5..f5625dd1b0 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/8c30bda73/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/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/8c30bda73/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index d9e428fa5d..a64f2b594c 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L40">memory.ts:40</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L32">memory.ts:32</a></li>
</ul>
</aside>
</section>
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L33">memory.ts:33</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L154">memory.ts:154</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L90">memory.ts:90</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L97">memory.ts:97</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L74">memory.ts:74</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L81">memory.ts:81</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L104">memory.ts:104</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L132">memory.ts:132</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L60">memory.ts:60</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L67">memory.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 053bc0bbb5..01e4ca1439 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 6f8d8f8578..fc50fc67fa 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 7527fbfc59..d85403d538 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index d8d0483ba0..7a695b398a 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 70061afb42..bdb2c5eea4 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index bc73db7b77..99df6ce132 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 0581e4eff3..dc612cc7c8 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 8bce1d9a89..4f9e89b19e 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 2b608be45b..4e8eb03ba5 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 5d16353a03..95b9b666d0 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 228fe289ef..6de4dc464e 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 027990f449..1eaa3e8a24 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8c30bda73/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/72c60ad78/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
... 957 lines suppressed ...