You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/12/08 21:47:02 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@9e7920b58107e55f1d05fcac4f75de87f94341e6)
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 43bf4c5ce1 deploying docs (apache/tvm@9e7920b58107e55f1d05fcac4f75de87f94341e6)
43bf4c5ce1 is described below
commit 43bf4c5ce138aff89131009899a5e9b00eb7c516
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Dec 8 21:46:55 2022 +0000
deploying docs (apache/tvm@9e7920b58107e55f1d05fcac4f75de87f94341e6)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 314727 -> 330120 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23008 -> 23754 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1819 ++------------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 27 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 843 +--------
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 11 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 39 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1819 ++------------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 27 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 843 +--------
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 | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 20 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
130 files changed, 1201 insertions(+), 5771 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 44d42e7073..749f250b96 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 979e8de9bd..eb961b1b9c 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 20299fa7be..89126831c8 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 9.583 seconds)
+ **Total running time of the script:** ( 1 minutes 8.642 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 00780d31c4..d7e4cf10da 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 945ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 938ms/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 1568ee8179..56ab69be9c 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.zipe5d2a290-443f-4a47-9f68-820649f70631 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf0ebeb96-5bcb-4004-8884-55b7ded0524e 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 b94a627a95..7a41e99737 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, 51.1MB/s]
27%|##7 | 11.2M/41.5M [00:00<00:00, 48.6MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 39.7MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 44.3MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 53.7MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 53.2MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 50.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.39M/41.5M [00:00<00:00, 67.0MB/s]
31%|### | 12.8M/41.5M [00:00<00:00, 56.3MB/s]
44%|####4 | 18.3M/41.5M [00:00<00:00, 44.3MB/s]
55%|#####4 | 22.7M/41.5M [00:00<00:00, 41.8MB/s]
67%|######7 | 27.9M/41.5M [00:00<00:00, 45.4MB/s]
78%|#######8 | 32.4M/41.5M [00:00<00:00, 46.1MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 51.2MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 50.2MB/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 d1f12d179b..f6aceb64f9 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, 77.2MB/s]
34%|###4 | 15.4M/44.7M [00:00<00:00, 70.2MB/s]
49%|####9 | 22.1M/44.7M [00:00<00:00, 67.0MB/s]
64%|######3 | 28.5M/44.7M [00:00<00:00, 64.4MB/s]
86%|########5 | 38.3M/44.7M [00:00<00:00, 77.3MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 66.7MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 75.1MB/s]
37%|###6 | 16.4M/44.7M [00:00<00:00, 82.4MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 99.2MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 102MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 97.8MB/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 843dbb7ff1..7b005c1dc2 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 12.157 seconds)
+ **Total running time of the script:** ( 1 minutes 11.531 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 8ee4932b8b..765be7ce9f 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
=================
-**05:43.877** total execution time for **how_to_compile_models** files:
+**05:40.209** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.157 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.531 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.583 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:08.642 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.953 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.801 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.399 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.128 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.047 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.857 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.488 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.447 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.338 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.536 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.167 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.917 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.304 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.946 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.442 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.403 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index a0092ce22a..c4f83ee09c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2686.8099 2686.6009 2690.7188 2685.4666 1.4030
+ 2687.3950 2686.7537 2692.0654 2685.4634 1.9608
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 996c01e12f..7800d8d54c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0373 15.6872 16.9190 15.6455 0.4964
+ 16.3516 16.3789 17.0786 15.8099 0.4488
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 9f65cc371e..f49f3ecc60 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
8%|7 | 12.9M/170M [00:00<00:01, 136MB/s]
15%|#5 | 25.9M/170M [00:00<00:02, 71.8MB/s]
20%|## | 34.2M/170M [00:00<00:01, 75.9MB/s]
25%|##4 | 42.5M/170M [00:00<00:01, 67.8MB/s]
29%|##9 | 49.5M/170M [00:00<00:01, 64.8MB/s]
34%|###3 | 57.6M/170M [00:00<00:01, 69.9MB/s]
38%|###8 | 64.6M/170M [00:00<00:01, 69.3MB/s]
45%|####4 | 76.3M/170M [00:01<00:01, 84.2MB/s]
50%|####9 | 84.8M/170M [00:01<00:01, 74.0MB/s]
56%|#####5 | 94.4M/170M [00:01<00:00, 81.1MB/s]
60%|###### | 103M/170M [00:01<00:00, 75.8MB/s]
66%|######5 | 112M/170M [00:01<00:00, 70.5MB/s]
73%|#######3 | 124M/170M [00:01<00:00, 84.8MB/s]
79%|#######9 | 134M/170M [00:01<00:00, 86.6MB/s]
84%|########4 | 143M/170M [00:01<00:00, 77.9MB/s]
89%|########8 | 151M/170M [00:02<00:00, 68.3MB/s]
94%|#########3| 159M/170M [00:02<00:00, 72.1MB/s]
98%|#########7| 166M/170M [00:02<00:00, 64.5MB/s]
100%|##########| 170M/170M [00:02<00:00, 73.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
6%|5 | 10.1M/170M [00:00<00:01, 95.8MB/s]
13%|#3 | 22.6M/170M [00:00<00:01, 116MB/s]
20%|#9 | 33.8M/170M [00:00<00:01, 90.5MB/s]
28%|##7 | 47.0M/170M [00:00<00:01, 106MB/s]
34%|###4 | 57.8M/170M [00:00<00:01, 78.5MB/s]
42%|####2 | 72.0M/170M [00:00<00:01, 85.7MB/s]
48%|####7 | 81.0M/170M [00:00<00:01, 80.1MB/s]
52%|#####2 | 89.1M/170M [00:01<00:01, 80.3MB/s]
57%|#####7 | 97.1M/170M [00:01<00:00, 77.7MB/s]
62%|######1 | 105M/170M [00:01<00:00, 74.3MB/s]
67%|######6 | 113M/170M [00:01<00:00, 78.4MB/s]
72%|#######2 | 123M/170M [00:01<00:00, 84.3MB/s]
79%|#######9 | 134M/170M [00:01<00:00, 87.6MB/s]
85%|########4 | 144M/170M [00:01<00:00, 83.1MB/s]
90%|######### | 153M/170M [00:01<00:00, 86.0MB/s]
95%|#########4| 161M/170M [00:02<00:00, 83.2MB/s]
100%|#########9| 169M/170M [00:02<00:00, 77.3MB/s]
100%|##########| 170M/170M [00:02<00:00, 83.4MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 16.740 seconds)
+ **Total running time of the script:** ( 3 minutes 14.882 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 40d83ddb13..15cf161ec2 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]
73%|#######2 | 9.84M/13.6M [00:00<00:00, 103MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 112MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
95%|#########4| 12.9M/13.6M [00:00<00:00, 135MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 132MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2997 90.2074 93.9229 90.0076 0.4177
+ 90.2519 90.1644 94.6986 90.0153 0.4671
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.906 seconds)
+ **Total running time of the script:** ( 1 minutes 5.957 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
index 4756d00938..dc0a6282c3 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.3177 119.2019 122.6607 118.5333 0.6330
+ 119.7810 119.7477 120.9401 118.8872 0.4089
@@ -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 22.560 seconds)
+ **Total running time of the script:** ( 2 minutes 23.145 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 375df8180b..87d407a75d 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 24.370 seconds)
+ **Total running time of the script:** ( 1 minutes 27.326 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 08a802c800..cad4f27b41 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5783/132723 [00:00<00:02, 57823.02KB/s]
10%|# | 13741/132723 [00:00<00:01, 70615.00KB/s]
16%|#6 | 21741/132723 [00:00<00:01, 74895.15KB/s]
22%|##2 | 29806/132723 [00:00<00:01, 77164.98KB/s]
28%|##8 | 37761/132723 [00:00<00:01, 78022.19KB/s]
35%|###4 | 45802/132723 [00:00<00:01, 78830.88KB/s]
41%|#### | 53779/132723 [00:00<00:00, 79135.62KB/s]
47%|####6 | 61837/132723 [00:00<00:00, 79592.30KB/s]
53%|#####2 | 69832/132723 [00:00<00:00, 79701.34KB/s]
59%|#####8 | 77803/132723 [00:01<00:00, 79647.24KB/s]
65%|######4 | 85784/132723 [00:01<00:00, 79693.73KB/s]
71%|####### | 93764/132723 [00:01<00:00, 79717.98KB/s]
77%|#######6 | 101748/132723 [00:01<00:00, 79749.43KB/s]
83%|########2 | 109746/132723 [00:01<00:00, 79816.31KB/s]
89%|########8 | 117728/132723 [00:01<00:00, 79542.04KB/s]
95%|########
#4| 125715/132723 [00:01<00:00, 79638.13KB/s]
100%|##########| 132723/132723 [00:01<00:00, 78462.69KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6036/132723 [00:00<00:02, 60355.88KB/s]
11%|#1 | 14673/132723 [00:00<00:01, 75655.37KB/s]
18%|#7 | 23323/132723 [00:00<00:01, 80603.62KB/s]
24%|##4 | 32033/132723 [00:00<00:01, 83165.65KB/s]
30%|### | 40350/132723 [00:00<00:01, 76549.95KB/s]
37%|###6 | 48930/132723 [00:00<00:01, 79522.29KB/s]
43%|####3 | 57627/132723 [00:00<00:00, 81863.00KB/s]
50%|####9 | 66298/132723 [00:00<00:00, 83365.51KB/s]
57%|#####6 | 75034/132723 [00:00<00:00, 84590.58KB/s]
63%|######3 | 83690/132723 [00:01<00:00, 85188.82KB/s]
70%|######9 | 92425/132723 [00:01<00:00, 85840.23KB/s]
76%|#######6 | 101156/132723 [00:01<00:00, 86283.43KB/s]
83%|########2 | 109874/132723 [00:01<00:00, 86550.86KB/s]
89%|########9 | 118538/132723 [00:01<00:00, 85820.56KB/s]
96%|#########5| 127192/132723 [00:01<00:00, 86032.97KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 83377.23KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 7.323 seconds)
+ **Total running time of the script:** ( 3 minutes 6.405 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 b4866d570e..7820023699 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**13:36.965** total execution time for **how_to_deploy_models** files:
+**13:35.961** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:16.740 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:14.882 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:07.323 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:06.405 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:22.560 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.145 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:24.370 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:27.326 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.906 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.957 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.355 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.142 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.640 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.542 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.266 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.841 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.799 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.715 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 23fbc23324..a147f4672c 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.zipcd8aa24e-03e3-4932-bceb-dbd0f76b4209 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip35890870-a81b-4c87-a19c-647bdfab48ac 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 52bad790e2..e7fe6a696f 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:47.495** total execution time for **how_to_extend_tvm** files:
+**00:47.776** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.998 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.299 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.453 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.432 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.036 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.037 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 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 82e4bb09c8..4b36c50fb0 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: 7171us [7171us] (46.41%; 46.41%)
- FoldScaleAxis: 8279us [6us] (53.59%; 53.59%)
- FoldConstant: 8272us [1704us] (53.54%; 99.92%)
- InferType: 6568us [6568us] (42.51%; 79.40%)
+ InferType: 7420us [7420us] (46.85%; 46.85%)
+ FoldScaleAxis: 8418us [6us] (53.15%; 53.15%)
+ FoldConstant: 8412us [1738us] (53.11%; 99.93%)
+ InferType: 6674us [6674us] (42.14%; 79.34%)
@@ -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: 6624us [6624us] (44.75%; 44.75%)
- FoldScaleAxis: 8177us [5us] (55.25%; 55.25%)
- FoldConstant: 8173us [1690us] (55.21%; 99.94%)
- InferType: 6483us [6483us] (43.80%; 79.33%)
+ InferType: 6597us [6597us] (44.96%; 44.96%)
+ FoldScaleAxis: 8078us [5us] (55.04%; 55.04%)
+ FoldConstant: 8073us [1668us] (55.01%; 99.94%)
+ InferType: 6405us [6405us] (43.65%; 79.34%)
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 a201264895..475694c7d0 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: 52.373729 ms
+ Convolution: 54.171905 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 c37c386cb4..f3145d1879 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.379773 ms
+ conv2d with tensor core: 13.376282 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 2efbf29013..291107cbe8 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: 0.018386
- Baseline: 3.365053
+ Numpy running time: 0.018521
+ Baseline: 3.341563
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.305447
+ Opt1: 0.300738
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.343218
+ Opt2: 0.337540
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114950
+ Opt3: 0.116263
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108336
+ Opt4: 0.109464
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111308
+ Opt5: 0.110901
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147381
+ Opt6: 0.146968
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 6cdd7096ba..f3137d3b2f 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.970** total execution time for **how_to_optimize_operators** files:
+**00:34.683** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.299 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.127 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.505 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.051 | 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 187e295efa..a31d8d8838 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:06.235** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:50.250** 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``) | 05:41.941 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:26.361 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.656 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.708 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.015 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.008 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.445 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:26.928 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.057 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.021 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.121 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.224 | 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 1c06573d97..d47b5a9e76 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
@@ -240,11 +240,11 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), 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" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [28], [], scope="local")[0] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local")[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -260,890 +260,80 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[13] = 0f32
conv2d_nchw_1[14] = 0f32
conv2d_nchw_1[15] = 0f32
- conv2d_nchw_1[16] = 0f32
- conv2d_nchw_1[17] = 0f32
- conv2d_nchw_1[18] = 0f32
- conv2d_nchw_1[19] = 0f32
- conv2d_nchw_1[20] = 0f32
- conv2d_nchw_1[21] = 0f32
- conv2d_nchw_1[22] = 0f32
- conv2d_nchw_1[23] = 0f32
- conv2d_nchw_1[24] = 0f32
- conv2d_nchw_1[25] = 0f32
- conv2d_nchw_1[26] = 0f32
- conv2d_nchw_1[27] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
+ 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" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1064), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1288), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1400), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1168)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1624), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1736), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1848), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[(threadIdx.x_1*6)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 3)*7)) + (ry.outer.outer [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 4)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtyp [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 5)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype [...]
+ }
}
- for (rc.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*147456) + (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" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 4), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 294), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 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" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 490), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 10), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 82), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 686), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 14), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (rx.outer.inner: int32, 0, 3) {
+ for (ff.outer.inner: int32, 0, 2) {
+ for (rc.inner: int32, 0, 4) {
+ let cse_var_10: int32 = (ff.outer.inner*8)
+ let cse_var_9: int32 = (cse_var_10 + 7)
+ let cse_var_8: int32 = (cse_var_10 + 6)
+ let cse_var_7: int32 = (cse_var_10 + 5)
+ let cse_var_6: int32 = (cse_var_10 + 4)
+ let cse_var_5: int32 = (cse_var_10 + 3)
+ let cse_var_4: int32 = (cse_var_10 + 2)
+ let cse_var_3: int32 = (cse_var_10 + 1)
+ {
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 48)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 96)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 120)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 168)]))
+ }
+ }
+ }
+ }
}
}
}
}
- for (i1.inner: int32, 0, 4) {
- for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 16) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*784)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*16)) + i1.inner)]), 0f32)
}
}
}
@@ -1198,7 +388,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.276 ms
+ Execution time of this operator: 0.322 ms
@@ -1246,20 +436,20 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=8)
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=8)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+ 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=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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)
@@ -1268,14 +458,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1295,14 +485,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ 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=98)
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=6)
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=56)
+ 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=98)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1320,10 +510,10 @@ 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__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[504];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1340,795 +530,58 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[14] = 0.000000e+00f;
conv2d_nchw[15] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
- conv2d_nchw[26] = 0.000000e+00f;
- conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ 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)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1168)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[(((int)threadIdx.x) * 6)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((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) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 2) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 4) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 294) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 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) + 490)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 490) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 10) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 82) {
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 686) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 14) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ conv2d_nchw[(ff_outer_inner * 8)] = (conv2d_nchw[(ff_outer_inner * 8)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 1)] = (conv2d_nchw[((ff_outer_inner * 8) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 2)] = (conv2d_nchw[((ff_outer_inner * 8) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 3)] = (conv2d_nchw[((ff_outer_inner * 8) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 4)] = (conv2d_nchw[((ff_outer_inner * 8) + 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 96)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 5)] = (conv2d_nchw[((ff_outer_inner * 8) + 5)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 120)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 6)] = (conv2d_nchw[((ff_outer_inner * 8) + 6)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 7)] = (conv2d_nchw[((ff_outer_inner * 8) + 7)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 168)]));
+ }
+ }
+ }
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 784)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 16)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -2190,7 +643,7 @@ 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 41.941 seconds)
+ **Total running time of the script:** ( 5 minutes 26.361 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 8a00715065..840186b9cd 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9061 7.9022 7.9147 7.9013 0.0061
+ 7.9069 7.9065 7.9131 7.9012 0.0049
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.015 seconds)
+ **Total running time of the script:** ( 1 minutes 2.008 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index b9aa92efe1..a97238ff5c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.7608 757.8931 760.0372 752.3521 3.2380
+ 751.7627 751.8361 753.1049 750.3471 1.1271
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.656 seconds)
+ **Total running time of the script:** ( 1 minutes 31.708 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 a72ebc10bd..6855e4eb7e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,28 +386,29 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 2) {
for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ compute_4: Buffer(compute_3, float32, [256], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 16) {
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 2) {
for (j: int32, 0, 16) {
- if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
- compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*4096) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_2, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -463,7 +464,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.531 ms
+ Execution time of this operator: 2.182 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 db6697b0b7..5097ec9327 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:27.684** total execution time for **how_to_tune_with_autotvm** files:
+**00:53.819** 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``) | 00:27.649 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:53.783 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 45e98a0ca3..5e56f625cf 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -387,8 +387,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10064893
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8765017
+ No: 2 GFLOPS: 6.92/6.92 result: MeasureResult(costs=(0.033444641,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2071523666381836, timestamp=1670534228.202493) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1064021
+ No: 3 GFLOPS: 0.00/6.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -510,8 +511,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7834570
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5786950
+ No: 4 GFLOPS: 0.00/6.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -633,8 +634,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1324824
- No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2077139
+ No: 5 GFLOPS: 0.00/6.92 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, 1, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4189440
+ No: 6 GFLOPS: 0.00/6.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -756,8 +775,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3054807
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6627620
+ No: 7 GFLOPS: 66.16/66.16 result: MeasureResult(costs=(0.003499268333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.989178419113159, timestamp=1670534242.2051907) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9008441
+ No: 8 GFLOPS: 0.00/66.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -879,8 +899,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7972071
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,382858
+ No: 9 GFLOPS: 0.00/66.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1002,9 +1022,11 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,852430
- No: 7 GFLOPS: 79.66/79.66 result: MeasureResult(costs=(0.002906020725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5092182159423828, timestamp=1670533421.405791) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4489994
- No: 8 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('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', 1)],None,5925668
+ No: 10 GFLOPS: 113.29/113.29 result: MeasureResult(costs=(0.002043401755102041,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6215996742248535, timestamp=1670534246.9681785) [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9392725
+ No: 11 GFLOPS: 246.78/246.78 result: MeasureResult(costs=(0.0009380924796747967,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.99544095993042, timestamp=1670534247.6343) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3588662
+ No: 12 GFLOPS: 143.26/246.78 result: MeasureResult(costs=(0.0016159303709677422,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.2158825397491455, timestamp=1670534248.3304582) [('tile_f', [-1, 1, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3886915
+ No: 13 GFLOPS: 0.00/246.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1126,8 +1148,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7330674
- No: 9 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1489074
+ No: 14 GFLOPS: 312.76/312.76 result: MeasureResult(costs=(0.0007401817801418438,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6705849170684814, timestamp=1670534250.1962533) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2226544
+ No: 15 GFLOPS: 0.00/312.76 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1249,8 +1272,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3206099
- No: 10 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1695743
+ No: 16 GFLOPS: 0.00/312.76 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1372,778 +1395,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1797223
- No: 11 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fdf16a72fa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
- Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8169256
- No: 12 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6062590
- No: 13 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7761691
- No: 14 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6687879
- No: 15 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10222511
- No: 16 GFLOPS: 274.36/274.36 result: MeasureResult(costs=(0.0008437847279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.343325138092041, timestamp=1670533428.3862648) [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3559233
- No: 17 GFLOPS: 0.00/274.36 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6517092
- No: 18 GFLOPS: 246.20/274.36 result: MeasureResult(costs=(0.0009403128130841122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9367525577545166, timestamp=1670533429.5178611) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5658480
- No: 19 GFLOPS: 0.00/274.36 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3052515
+ No: 17 GFLOPS: 84.21/312.76 result: MeasureResult(costs=(0.002749206904761905,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6787645816802979, timestamp=1670534258.3552167) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7005518
+ No: 18 GFLOPS: 0.00/312.76 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2265,8 +1519,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9931119
- No: 20 GFLOPS: 0.00/274.36 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7134889
+ No: 19 GFLOPS: 500.65/500.65 result: MeasureResult(costs=(0.00046240396017699115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.637235641479492, timestamp=1670534259.0428703) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10360681
+ No: 20 GFLOPS: 0.00/500.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2388,7 +1643,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6664114
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1059350
@@ -2443,9 +1698,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3559233
+ [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10360681
Finish loading 20 records
- Time cost of this operator: 0.001178
+ Time cost of this operator: 0.000838
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 fa973c1896..449b395426 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.5 98.715 (1, 2, 10, 10, 3) 2 1 [311.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.069 0.973 (1, 6, 10, 10) 1 1 [3.069]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.986 0.312 (1, 1, 10, 10, 3) 1 1 [0.986]
- Total_time - 315.555 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.3 98.734 (1, 2, 10, 10, 3) 2 1 [312.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.955 (1, 6, 10, 10) 1 1 [3.021]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.311 (1, 1, 10, 10, 3) 1 1 [0.984]
+ Total_time - 316.305 - - - - -
@@ -397,10 +397,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 137.0 98.0 (1, 6, 10, 10, 1) 2 1 [137.0]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.832 1.31 (1, 6, 10, 10) 1 1 [1.832]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.689 (1, 1, 10, 10, 3) 1 1 [0.964]
- Total_time - 139.795 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 105.3 97.574 (1, 6, 10, 10, 1) 2 1 [105.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.778 1.648 (1, 6, 10, 10) 1 1 [1.778]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.778 (1, 3, 10, 10, 1) 1 1 [0.84]
+ Total_time - 107.918 - - - - -
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 75cedf8769..4abe440794 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]
100%|##########| 3.42M/3.42M [00:00<00:00, 42.6MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 43.9MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.863 seconds)
+ **Total running time of the script:** ( 1 minutes 3.819 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 4e20ea0c89..a22388774a 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/tmpt2fbb_2z/images/random'
+ '/tmp/tmpufmxekuo/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
: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/tmpt2fbb_2z/images/target contains 8144 images
- /tmp/tmpt2fbb_2z/images/random contains 5000 images
+ /tmp/tmpufmxekuo/images/target contains 8144 images
+ /tmp/tmpufmxekuo/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2308 - accuracy: 0.9210 - val_loss: 0.1362 - val_accuracy: 0.9539 - 47s/epoch - 142ms/step
+ 328/328 - 47s - loss: 0.2660 - accuracy: 0.9131 - val_loss: 0.1781 - val_accuracy: 0.9456 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1019 - accuracy: 0.9625 - val_loss: 0.1074 - val_accuracy: 0.9641 - 43s/epoch - 132ms/step
+ 328/328 - 44s - loss: 0.1013 - accuracy: 0.9647 - val_loss: 0.1111 - val_accuracy: 0.9622 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0687 - accuracy: 0.9742 - val_loss: 0.1171 - val_accuracy: 0.9660 - 43s/epoch - 131ms/step
+ 328/328 - 44s - loss: 0.0703 - accuracy: 0.9748 - val_loss: 0.1128 - val_accuracy: 0.9664 - 44s/epoch - 133ms/step
- <keras.callbacks.History object at 0x7ff88a5d6910>
+ <keras.callbacks.History object at 0x7f72fc8a6c10>
@@ -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 23.544 seconds)
+ **Total running time of the script:** ( 4 minutes 19.202 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 b627ae8041..eb6109820b 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:29.326** total execution time for **how_to_work_with_microtvm** files:
+**06:24.816** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:23.544 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:19.202 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:03.863 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:03.819 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.271 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.181 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.869 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.817 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.777 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.794 | 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 b1438c1102..45e04b3ad9 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
=================
-**00:44.303** total execution time for **how_to_work_with_relay** files:
+**00:44.321** 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``) | 00:32.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.414 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.244 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.146 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.553 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.754 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 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 427efd39f4..56a4a63011 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 0x7ff8e82d0170>
+ <function my_cuda_math_rule at 0x7f72f3422050>
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 888902bc41..38e93ab64b 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
=================
-**00:06.796** total execution time for **how_to_work_with_schedules** files:
+**00:07.969** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.318 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.457 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.129 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.162 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.577 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.556 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.023 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index f3040cb875..fdc6ac7d26 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpb1xpvrmc/input0.cc'\nsource_filename = \"/tmp/tmpb1xpvrmc/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/tmp2dgve0xt/input0.cc'\nsource_filename = \"/tmp/tmp2dgve0xt/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 2ff0beeb8c..4e70b94c4d 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:26.283** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.250** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.277 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.244 | 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 a09f4b44c6..e569487bee 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 28.92s!
+ resnet18_v1 inference graph built in 29.03s!
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 e6a9648446..78907f30c4 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 19.54s!
+ yolov3-tiny inference graph built in 19.55s!
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 a4e59a4bf9..60d7c560fe 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
=================
-**01:40.044** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.325** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.245 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.505 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.799 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.820 | 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 820a5602dd..007e6b67c7 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.184** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.179** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.721 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.732 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.462 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.447 | 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 43f7423925..61c3739145 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
=================
-**00:00.791** total execution time for **topic_vta_tutorials** files:
+**00:00.792** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.417 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.420 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.374 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.372 | 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 daead3964e..5b65971c1e 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -325,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 96.057 ms
+ Execution time of this operator: 94.386 ms
@@ -443,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.474 seconds)
+ **Total running time of the script:** ( 1 minutes 32.627 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 8077632be7..d26788e316 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: 9.10/9.10 result: MeasureResult(costs=(0.029494057199999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6937284469604492, timestamp=1670532006.0533361) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
- No: 2 GFLOPS: 11.66/11.66 result: MeasureResult(costs=(0.0230270318,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6215167045593262, timestamp=1670532006.6331725) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
- No: 3 GFLOPS: 13.39/13.39 result: MeasureResult(costs=(0.0200469796,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.490020751953125, timestamp=1670532007.8975756) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
- No: 4 GFLOPS: 1.76/13.39 result: MeasureResult(costs=(0.1526547732,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.603560447692871, timestamp=1670532011.2719052) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
- No: 5 GFLOPS: 10.53/13.39 result: MeasureResult(costs=(0.025485432599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5703213214874268, timestamp=1670532011.988707) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 6 GFLOPS: 12.18/13.39 result: MeasureResult(costs=(0.022042364000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5228996276855469, timestamp=1670532012.5114086) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
- No: 7 GFLOPS: 10.15/13.39 result: MeasureResult(costs=(0.0264338216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6265871524810791, timestamp=1670532013.8651066) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
- No: 8 GFLOPS: 12.83/13.39 result: MeasureResult(costs=(0.020914511599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.517465353012085, timestamp=1670532014.4109683) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
- No: 9 GFLOPS: 0.89/13.39 result: MeasureResult(costs=(0.300435376,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.920586347579956, timestamp=1670532019.4459367) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
- No: 10 GFLOPS: 0.50/13.39 result: MeasureResult(costs=(0.5360208743999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.697869062423706, timestamp=1670532028.1963308) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+ No: 1 GFLOPS: 1.45/1.45 result: MeasureResult(costs=(0.1852069236,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1130270957946777, timestamp=1670532811.7613292) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 2 GFLOPS: 12.45/12.45 result: MeasureResult(costs=(0.0215588942,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5549671649932861, timestamp=1670532812.315152) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
+ No: 3 GFLOPS: 0.50/12.45 result: MeasureResult(costs=(0.5332061122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.678447723388672, timestamp=1670532821.7711987) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+ No: 4 GFLOPS: 7.92/12.45 result: MeasureResult(costs=(0.0339078824,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6759617328643799, timestamp=1670532823.2448962) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+ No: 5 GFLOPS: 1.52/12.45 result: MeasureResult(costs=(0.17633714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9707956314086914, timestamp=1670532826.439865) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+ No: 6 GFLOPS: 11.48/12.45 result: MeasureResult(costs=(0.0233840282,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5285539627075195, timestamp=1670532827.7331326) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
+ No: 7 GFLOPS: 9.70/12.45 result: MeasureResult(costs=(0.027661951599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6976029872894287, timestamp=1670532828.3446784) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
+ No: 8 GFLOPS: 12.67/12.67 result: MeasureResult(costs=(0.021178358,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6313397884368896, timestamp=1670532828.8928554) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+ No: 9 GFLOPS: 9.10/12.67 result: MeasureResult(costs=(0.029491357399999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6601502895355225, timestamp=1670532829.6961339) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+ No: 10 GFLOPS: 13.05/13.05 result: MeasureResult(costs=(0.020568988,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5492422580718994, timestamp=1670532830.195749) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 09a7ff88d8..ccb41639be 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': 513.6498611600007, 'median': 512.9932505999989, 'std': 2.8798782377045864}
+ {'mean': 514.4685151600027, 'median': 514.7692598500043, 'std': 2.0755005781498563}
@@ -554,29 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 3.19/ 23.29 GFLOPS | Progress: (4/20) | 7.46 s
[Task 1/25] Current/Best: 8.42/ 23.29 GFLOPS | Progress: (8/20) | 11.84 s
[Task 1/25] Current/Best: 18.33/ 23.29 GFLOPS | Progress: (12/20) | 15.04 s
[Task 1/25] Current/Best: 15.53/ 23.29 GFLOPS | Progress: (16/20) | 17.18 s
[Task 1/25] Current/Best: 11.14/ 23.29 GFLOPS | Progress: (20/20) | 18.96 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 13.35/ 14.67 GFLOPS | Progress: (4/20) | 3.07 s
[Task 2/25] Current/Best: 17.09/ 17.72 GFLOPS | Progress: (8/20) | 4.16 s
[Task 2/25] Current/Best: 3.34/ 18.56 GFLOPS | Progress: (12/20) | 5.49 s
[Task 2/25] Current/Best: 5.87/ 18.56 GFLOPS | Progress: (16/20) | 6.88 s
[Task 2/25] Current/Best: 15.09/ 18.56 GFLOPS | Progress: (20/20) | 8.33 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 9.24/ 21.22 GFLOPS | Progress: (4/20) | 4.17 s
[Task 3/25] Current/Best: 10.11/ 21.22 GFLOPS | Progress: (8/20) | 6.92 s
[Task 3/25] Current/Best: 9.70/ 21.22 GFLOPS | Progress: (12/20) | 9.30 s
[Task 3/25] Current/Best: 7.87/ 21.22 GFLOPS | Progress: (16/20) | 11.57 s
[Task 3/25] Current/Best: 14.01/ 21.22 GFLOPS | Progress: (20/20) | 13.63 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.15/ 14.27 GFLOPS | Progress: (4/20) | 3.51 s
[Task 4/25] Current/Best: 3.89/ 17.48 GFLOPS | Progress: (8/20) | 14.50 s
[Task 4/25] Current/Best: 22.03/ 22.03 GFLOPS | Progress: (12/20) | 16.75 s
[Task 4/25] Current/Best: 16.14/ 22.03 GFLOPS | Progress: (16/20) | 18.59 s
[Task 4/25] Current/Best: 11.96/ 22.03 GFLOPS | Progress: (20/20) | 23.12 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 15.02/ 18.40 GFLOPS | Progress: (4/20) | 2.93 s
[Task 5/25] Current/Best: 5.11/ 18.40 GFLOPS | Progress: (8/20) | 4.67 s
[Task 5/25] Current/Best: 11.05/ 18.40 GFLOPS | Progress: (12/20) | 6.97 s
[Task 5/25] Current/Best: 13.47/ 18.40 GFLOPS | Progress: (16/20) | 8.70 s
[Task 5/25] Current/Best: 5.64/ 20.54 GFLOPS | Progress: (20/20) | 10.28 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.51/ 14.51 GFLOPS | Progress: (4/20) | 4.36 s
[Task 6/25] Current/Best: 5.37/ 19.43 GFLOPS | Progress: (8/20) | 7.74 s
[Task 6/25] Current/Best: 17.50/ 19.43 GFLOPS | Progress: (12/20) | 9.75 s
[Task 6/25] Current/Best: 2.80/ 19.43 GFLOPS | Progress: (16/20) | 12.52 s
[Task 6/25] Current/Best: 12.64/ 19.43 GFLOPS | Progress: (20/20) | 14.47 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.82/ 17.52 GFLOPS | Progress: (4/20) | 3.91 s
[Task 7/25] Current/Best: 15.36/ 18.47 GFLOPS | Progress: (8/20) | 6.06 s
[Task 7/25] Current/Best: 8.59/ 18.47 GFLOPS | Progress: (12/20) | 8.21 s
[Task 7/25] Current/Best: 17.40/ 18.47 GFLOPS | Progress: (16/20) | 10.74 s
[Task 7/25] Current/Best: 6.29/ 18.47 GFLOPS | Progress: (20/20) | 13.07 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.05/ 20.76 GFLOPS | Progress: (4/20) | 3.53 s
[Task 8/25] Current/Best: 3.18/ 20.76 GFLOPS | Progress: (8/20) | 6.19 s
[Task 8/25] Current/Best: 12.18/ 20.76 GFLOPS | Progress: (12/20) | 10.33 s
[Task 8/25] Current/Best: 2.99/ 20.76 GFLOPS | Progress: (16/20) | 12.45 s
[Task 8/25] Current/Best: 10.80/ 20.76 GFLOPS | Progress: (20/20) | 15.33 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.43/ 17.14 GFLOPS | Progress: (4/20) | 5.99 s
[Task 9/25] Current/Best: 6.74/ 17.14 GFLOPS | Progress: (8/20) | 11.27 s
[Task 9/25] Current/Best: 6.35/ 21.63 GFLOPS | Progress: (12/20) | 22.15 s
[Task 9/25] Current/Best: 6.51/ 21.63 GFLOPS | Progress: (16/20) | 24.33 s
[Task 9/25] Current/Best: 9.93/ 21.63 GFLOPS | Progress: (20/20) | 32.89 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.00/ 17.81 GFLOPS | Progress: (4/20) | 3.47 s
[Task 10/25] Current/Best: 10.82/ 17.81 GFLOPS | Progress: (8/20) | 4.97 s
[Task 10/25] Current/Best: 8.94/ 17.81 GFLOPS | Progress: (12/20) | 6.61 s
[Task 10/25] Current/Best: 3.85/ 17.81 GFLOPS | Progress: (16/20) | 8.86 s
[Task 10/25] Current/Best: 16.23/ 17.81 GFLOPS | Progress: (20/20)
| 11.18 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 7.76/ 16.20 GFLOPS | Progress: (4/20) | 3.56 s
[Task 11/25] Current/Best: 8.41/ 16.20 GFLOPS | Progress: (8/20) | 6.00 s
[Task 11/25] Current/Best: 12.56/ 16.20 GFLOPS | Progress: (12/20) | 9.31 s
[Task 11/25] Current/Best: 16.39/ 17.25 GFLOPS | Progress: (16/20) | 11.49 s
[Task 11/25] Current/Best: 18.42/ 18.42 GFLOPS | Progress: (20/20) | 13.37 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.49/ 14.50 GFLOPS | Progress: (4/20) | 4.02 s
[Task 12/25] Current/Best: 3.12/ 18.34 GFLOPS | Progress: (8/20) | 6.21 s
[Task 12/25] Current/Best: 9.12/ 19.72 GFLOPS | Progress: (12/20) | 14.60 s
[Task 12/25] Current/Best: 6.99/ 19.72 GFLOPS | Progress: (16/20) | 16.50 s
[Task 12/25] Current/Best: 13.33/ 19.72 GFLOPS | Progress: (20/20) | 18.72 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 22.71/ 22.71 GFLOPS | Progress: (4/20) | 3.57 s
[Task 13/25] Current/Best: 18.51/ 22.71 GFLOPS | Progress: (8/20) | 5.81 s
[Task 13/25] Current/Best: 13.82/ 22.71 GFLOPS | Progress: (12/20) | 9.09 s
[Task 13/25] Current/Best: 17.89/ 22.71 GFLOPS | Progress: (16/20) | 12.02 s
[Task 13/25] Current/Best: 12.18/ 22.71 GFLOPS | Progress: (20/20) | 15.10 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 17.39/ 17.39 GFLOPS | Progress: (4/20) | 3.18 s
[Task 14/25] Current/Best: 7.17/ 17.52 GFLOPS | Progress: (8/20) | 6.44 s
[Task 14/25] Current/Best: 9.99/ 17.52 GFLOPS | Progress: (12/20) | 8.63 s
[Task 14/25] Current/Best: 13.25/ 17.52 GFLOPS | Progress: (16/20) | 12.90 s Done.
-
[Task 14/25] Current/Best: 13.03/ 17.52 GFLOPS | Progress: (20/20) | 15.45 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 12.27/ 13.23 GFLOPS | Progress: (4/20) | 4.88 s
[Task 15/25] Current/Best: 15.70/ 15.70 GFLOPS | Progress: (8/20) | 7.88 s
[Task 15/25] Current/Best: 16.47/ 19.02 GFLOPS | Progress: (12/20) | 9.33 s
[Task 15/25] Current/Best: 18.42/ 20.56 GFLOPS | Progress: (16/20) | 10.60 s
[Task 15/25] Current/Best: 6.35/ 20.56 GFLOPS | Progress: (20/20) | 12.23 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 3.11/ 15.11 GFLOPS | Progress: (4/20) | 4.61 s
[Task 16/25] Current/Best: 10.92/ 17.66 GFLOPS | Progress: (8/20) | 5.90 s
[Task 16/25] Current/Best: 16.54/ 20.79 GFLOPS | Progress: (12/20) | 7.28 s
[Task 16/25] Current/Best: 15.14/ 20.88 GFLOPS | Progress: (16/20) | 8.63 s
[Task 16/25] Current/Best: 5.70/ 20.88 GFLOPS | Progress: (20/20) | 9.95 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.27/ 19.61 GFLOPS | Progress: (4/20) | 3.14 s
[Task 17/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (8/20) | 5.58 s
[Task 17/25] Current/Best: 6.14/ 19.77 GFLOPS | Progress: (12/20) | 7.89 s
[Task 17/25] Current/Best: 18.39/ 21.30 GFLOPS | Progress: (16/20) | 9.83 s
[Task 17/25] Current/Best: 22.55/ 22.55 GFLOPS | Progress: (20/20) | 12.27 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 14.50/ 14.50 GFLOPS | Progress: (4/20) | 5.03 s
[Task 18/25] Current/Best: 19.54/ 19.96 GFLOPS | Progress: (8/20) | 10.61 s
[Task 18/25] Current/Best: 20.79/ 20.79 GFLOPS | Progress: (12/20) | 12.06 s
[Task 18/25] Current/Best: 9.65/ 20.79 GFLOPS | Progress: (16/20) | 14.29 s
[Task 18/25] Current/Best: 14.41/ 20.79 GFLOPS | Progress: (20/20) | 17.84 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 17.82/ 17.82 GFLOPS | Progress: (4/20) | 5.40 s
[Task 19/25] Current/Best: 20.90/ 20.90 GFLOPS | Progress: (8/20) | 9.64 s
[Task 19/25] Current/Best: 5.27/ 20.90 GFLOPS | Progress: (12/20) | 13.12 s
[Task 19/25] Current/Best: 14.62/ 20.90 GFLOPS | Progress: (16/20) | 15.92 s
[Task 19/25] Current/Best: 11.32/ 20.90 GFLOPS | Progress: (20/20) | 21.47 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 7.22/ 14.01 GFLOPS | Progress: (4/20) | 7.22 s
[Task 20/25] Current/Best: 2.68/ 14.01 GFLOPS | Progress: (8/20) | 11.18 s
[Task 20/25] Current/Best: 12.45/ 14.01 GFLOPS | Progress: (12/20) | 12.99 s
[Task 20/25] Current/Best: 8.02/ 17.66 GFLOPS | Progress: (16/20) | 16.25 s
[Task 20/25] Current/Best: 3.08/ 17.66 GFLOPS | Progress: (20/20) | 19.67 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 5.22/ 15.60 GFLOPS | Progress: (4/20) | 3.15 s
[Task 21/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (8/20) | 4.50 s
[Task 21/25] Current/Best: 18.10/ 18.50 GFLOPS | Progress: (12/20) | 6.21 s
[Task 21/25] Current/Best: 16.59/ 18.50 GFLOPS | Progress: (16/20) | 7.96 s Done.
-
[Task 21/25] Current/Best: 20.78/ 20.78 GFLOPS | Progress: (20/20) | 11.31 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 9.11/ 16.46 GFLOPS | Progress: (4/20) | 3.62 s
[Task 22/25] Current/Best: 13.69/ 16.46 GFLOPS | Progress: (8/20) | 5.18 s
[Task 22/25] Current/Best: 7.88/ 16.46 GFLOPS | Progress: (12/20) | 6.77 s
[Task 22/25] Current/Best: 18.69/ 18.84 GFLOPS | Progress: (16/20) | 8.14 s
[Task 22/25] Current/Best: 10.36/ 18.84 GFLOPS | Progress: (20/20) | 9.78 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.62/ 19.19 GFLOPS | Progress: (4/20) | 4.66 s
[Task 23/25] Current/Best: 3.08/ 19.19 GFLOPS | Progress: (8/20) | 8.06 s
[Task 23/25] Current/Best: 23.60/ 23.60 GFLOPS | Progress: (12/20) | 9.71 s
[Task 23/25] Current/Best: 1.55/ 23.60 GFLOPS | Progress: (16/20) | 15.64 s
[Task 23/25] Current/Best: 18.29/ 23.60 GFLOPS | Progress: (20/20) | 17.88 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 2.28/ 6.74 GFLOPS | Progress: (4/20) | 12.27 s
[Task 24/25] Current/Best: 6.05/ 6.74 GFLOPS | Progress: (8/20) | 23.51 s
[Task 24/25] Current/Best: 5.72/ 9.74 GFLOPS | Progress: (12/20) | 31.28 s
[Task 24/25] Current/Best: 3.62/ 9.74 GFLOPS | Progress: (16/20) | 42.01 s
[Task 24/25] Current/Best: 2.28/ 9.74 GFLOPS | Progress: (20/20) | 45.87 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 9.21/ 9.21 GFLOPS | Progress: (4/20) | 11.51 s
[Task 25/25] Current/Best: 7.02/ 9.61 GFLOPS | Progress: (8/20) | 12.58 s
[Task 25/25] Current/Best: 3.40/ 9.61 GFLOPS | Progress: (12/20) | 23.11 s
[Task 25/25] Current/Best: 1.55/ 9.61 GFLOPS | Progress: (16/20) | 35.03 s
[Task 25/25] Current/Best: 5.73/ 9.61 GFLOPS | Progress: (20/20) | 39.76 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 13.54/ 18.74 GFLOPS | Progress: (4/20) | 6.18 s
[Task 1/25] Current/Best: 8.62/ 18.74 GFLOPS | Progress: (8/20) | 11.69 s
[Task 1/25] Current/Best: 16.19/ 18.74 GFLOPS | Progress: (12/20) | 13.75 s
[Task 1/25] Current/Best: 23.44/ 23.44 GFLOPS | Progress: (16/20) | 15.58 s
[Task 1/25] Current/Best: 6.08/ 23.44 GFLOPS | Progress: (20/20) | 18.04 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 21.71/ 21.71 GFLOPS | Progress: (4/20) | 2.55 s
[Task 2/25] Current/Best: 12.07/ 21.71 GFLOPS | Progress: (8/20) | 3.88 s
[Task 2/25] Current/Best: 15.63/ 21.71 GFLOPS | Progress: (12/20) | 5.43 s
[Task 2/25] Current/Best: 12.21/ 21.71 GFLOPS | Progress: (16/20) | 6.72 s
[Task 2/25] Current/Best: 16.12/ 21.71 GFLOPS | Progress: (20/20) | 8.16 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.49/ 14.23 GFLOPS | Progress: (4/20) | 3.54 s
[Task 3/25] Current/Best: 9.17/ 17.34 GFLOPS | Progress: (8/20) | 5.35 s
[Task 3/25] Current/Best: 6.26/ 17.34 GFLOPS | Progress: (12/20) | 9.24 s
[Task 3/25] Current/Best: 6.36/ 19.79 GFLOPS | Progress: (16/20) | 11.19 s
[Task 3/25] Current/Best: 22.77/ 22.77 GFLOPS | Progress: (20/20) | 13.27 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.98/ 18.19 GFLOPS | Progress: (4/20) | 5.49 s
[Task 4/25] Current/Best: 18.10/ 18.19 GFLOPS | Progress: (8/20) | 7.10 s
[Task 4/25] Current/Best: 6.55/ 18.19 GFLOPS | Progress: (12/20) | 12.97 s
[Task 4/25] Current/Best: 10.08/ 18.19 GFLOPS | Progress: (16/20) | 15.05 s
[Task 4/25] Current/Best: 10.90/ 18.19 GFLOPS | Progress: (20/20) | 17.21 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 4.12/ 19.08 GFLOPS | Progress: (4/20) | 3.67 s
[Task 5/25] Current/Best: 9.75/ 19.08 GFLOPS | Progress: (8/20) | 5.55 s
[Task 5/25] Current/Best: 14.49/ 19.08 GFLOPS | Progress: (12/20) | 7.55 s
[Task 5/25] Current/Best: 9.76/ 19.08 GFLOPS | Progress: (16/20) | 9.62 s
[Task 5/25] Current/Best: 14.24/ 19.08 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: 20.64/ 20.64 GFLOPS | Progress: (4/20) | 7.65 s
[Task 6/25] Current/Best: 15.79/ 20.64 GFLOPS | Progress: (8/20) | 10.16 s
[Task 6/25] Current/Best: 11.59/ 20.64 GFLOPS | Progress: (12/20) | 12.28 s
[Task 6/25] Current/Best: 15.96/ 20.64 GFLOPS | Progress: (16/20) | 15.29 s
[Task 6/25] Current/Best: 19.78/ 20.64 GFLOPS | Progress: (20/20) | 17.40 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.04/ 16.69 GFLOPS | Progress: (4/20) | 3.71 s
[Task 7/25] Current/Best: 18.76/ 20.36 GFLOPS | Progress: (8/20) | 6.04 s
[Task 7/25] Current/Best: 14.12/ 20.36 GFLOPS | Progress: (12/20) | 9.78 s
[Task 7/25] Current/Best: 11.66/ 20.36 GFLOPS | Progress: (16/20) | 11.94 s
[Task 7/25] Current/Best: 11.69/ 20.36 GFLOPS | Progress: (20/20) | 13.99 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (4/20) | 4.69 s
[Task 8/25] Current/Best: 2.53/ 19.64 GFLOPS | Progress: (8/20) | 8.06 s
[Task 8/25] Current/Best: 10.43/ 19.92 GFLOPS | Progress: (12/20) | 18.68 s
[Task 8/25] Current/Best: 10.65/ 19.92 GFLOPS | Progress: (16/20) | 22.62 s
[Task 8/25] Current/Best: 8.03/ 19.92 GFLOPS | Progress: (20/20) | 25.13 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 3.12/ 22.38 GFLOPS | Progress: (4/20) | 3.01 s
[Task 9/25] Current/Best: 13.33/ 22.38 GFLOPS | Progress: (8/20) | 5.31 s
[Task 9/25] Current/Best: 14.14/ 22.38 GFLOPS | Progress: (12/20) | 7.62 s
[Task 9/25] Current/Best: 8.53/ 22.38 GFLOPS | Progress: (16/20) | 14.61 s
[Task 9/25] Current/Best: 19.64/ 22.38 GFLOPS | Progress: (20/20) | 16.40 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.37/ 17.30 GFLOPS | Progress: (4/20) | 2.91 s
[Task 10/25] Current/Best: 10.29/ 17.30 GFLOPS | Progress: (8/20) | 5.17 s
[Task 10/25] Current/Best: 15.30/ 17.30 GFLOPS | Progress: (12/20) | 6.71 s
[Task 10/25] Current/Best: 4.29/ 17.98 GFLOPS | Progress: (16/20) | 8.62 s
[Task 10/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (20/20) | 11.46 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 18.00/ 18.00 GFLOPS | Progress: (4/20) | 3.47 s
[Task 11/25] Current/Best: 10.73/ 18.59 GFLOPS | Progress: (8/20) | 5.90 s
[Task 11/25] Current/Best: 19.37/ 23.92 GFLOPS | Progress: (12/20) | 7.73 s
[Task 11/25] Current/Best: 6.16/ 23.92 GFLOPS | Progress: (16/20) | 10.01 s
[Task 11/25] Current/Best: 20.74/ 23.92 GFLOPS | Progress: (20/20) | 12.03 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 4.75 s
[Task 12/25] Current/Best: 4.22/ 21.65 GFLOPS | Progress: (8/20) | 7.14 s
[Task 12/25] Current/Best: 12.71/ 21.65 GFLOPS | Progress: (12/20) | 9.29 s
[Task 12/25] Current/Best: 10.77/ 21.65 GFLOPS | Progress: (16/20) | 11.46 s
[Task 12/25] Current/Best: 10.01/ 21.65 GFLOPS | Progress: (20/20) | 13.65 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.88/ 20.74 GFLOPS | Progress: (4/20) | 3.58 s
[Task 13/25] Current/Best: 8.59/ 20.74 GFLOPS | Progress: (8/20) | 7.01 s
[Task 13/25] Current/Best: 18.26/ 20.74 GFLOPS | Progress: (12/20) | 9.46 s
[Task 13/25] Current/Best: 3.07/ 20.74 GFLOPS | Progress: (16/20) | 13.15 s
[Task 13/25] Current/Best: 21.12/ 21.68 GFLOPS | Progress: (20/20) | 14.96 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.02/ 17.44 GFLOPS | Progress: (4/20) | 3.93 s
[Task 14/25] Current/Best: 3.72/ 19.08 GFLOPS | Progress: (8/20) | 7.50 s
[Task 14/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (12/20) | 9.76 s
[Task 14/25] Current/Best: 15.26/ 21.19 GFLOPS | Progress: (16/20) | 15.51 s
[Task 14/25] Current/Best: 6.04/ 21.19 GFLOPS | Progress: (20/20) | 18.08 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.43/ 13.43 GFLOPS | Progress: (4/20) | 3.52 s
[Task 15/25] Current/Best: 19.47/ 19.47 GFLOPS | Progress: (8/20) | 5.44 s
[Task 15/25] Current/Best: 4.75/ 20.69 GFLOPS | Progress: (12/20) | 7.57 s Done.
+
[Task 15/25] Current/Best: 7.47/ 20.69 GFLOPS | Progress: (16/20) | 10.38 s
[Task 15/25] Current/Best: 13.29/ 20.69 GFLOPS | Progress: (20/20) | 11.60 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.81/ 18.56 GFLOPS | Progress: (4/20) | 3.58 s
[Task 16/25] Current/Best: 3.10/ 18.56 GFLOPS | Progress: (8/20) | 5.08 s
[Task 16/25] Current/Best: 17.23/ 18.56 GFLOPS | Progress: (12/20) | 6.81 s
[Task 16/25] Current/Best: 11.84/ 18.56 GFLOPS | Progress: (16/20) | 8.63 s
[Task 16/25] Current/Best: 11.97/ 18.56 GFLOPS | Progress: (20/20) | 10.79 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.86/ 16.50 GFLOPS | Progress: (4/20) | 3.92 s
[Task 17/25] Current/Best: 1.56/ 19.09 GFLOPS | Progress: (8/20) | 7.50 s
[Task 17/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 9.23 s
[Task 17/25] Current/Best: 11.18/ 23.98 GFLOPS | Progress: (16/20) | 12.97 s
[Task 17/25] Current/Best: 3.10/ 23.98 GFLOPS | Progress: (20/20) | 15.74 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 12.20/ 13.63 GFLOPS | Progress: (4/20) | 3.77 s
[Task 18/25] Current/Best: 8.74/ 14.34 GFLOPS | Progress: (8/20) | 6.50 s
[Task 18/25] Current/Best: 6.24/ 16.16 GFLOPS | Progress: (12/20) | 8.34 s
[Task 18/25] Current/Best: 16.56/ 16.56 GFLOPS | Progress: (16/20) | 12.07 s
[Task 18/25] Current/Best: 16.51/ 18.05 GFLOPS | Progress: (20/20) | 13.54 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (4/20) | 3.57 s
[Task 19/25] Current/Best: 18.03/ 18.90 GFLOPS | Progress: (8/20) | 8.06 s
[Task 19/25] Current/Best: 10.76/ 18.90 GFLOPS | Progress: (12/20) | 11.21 s
[Task 19/25] Current/Best: 17.84/ 18.90 GFLOPS | Progress: (16/20) | 14.25 s
[Task 19/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (20/20) | 17.57 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 15.25/ 15.25 GFLOPS | Progress: (4/20) | 6.39 s
[Task 20/25] Current/Best: 7.44/ 18.24 GFLOPS | Progress: (8/20) | 8.11 s
[Task 20/25] Current/Best: 10.43/ 18.24 GFLOPS | Progress: (12/20) | 10.58 s
[Task 20/25] Current/Best: 11.96/ 18.24 GFLOPS | Progress: (16/20) | 13.69 s
[Task 20/25] Current/Best: 6.39/ 18.24 GFLOPS | Progress: (20/20) | 16.39 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 16.20/ 16.93 GFLOPS | Progress: (4/20) | 3.69 s
[Task 21/25] Current/Best: 16.74/ 16.93 GFLOPS | Progress: (8/20) | 8.13 s
[Task 21/25] Current/Best: 9.60/ 19.18 GFLOPS | Progress: (12/20) | 9.51 s Done.
+ Done.
+
[Task 21/25] Current/Best: 12.04/ 19.18 GFLOPS | Progress: (16/20) | 11.92 s
[Task 21/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (20/20) | 14.21 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.11/ 18.71 GFLOPS | Progress: (4/20) | 6.04 s
[Task 22/25] Current/Best: 14.39/ 18.71 GFLOPS | Progress: (8/20) | 7.65 s
[Task 22/25] Current/Best: 19.46/ 19.46 GFLOPS | Progress: (12/20) | 9.37 s
[Task 22/25] Current/Best: 12.75/ 19.46 GFLOPS | Progress: (16/20) | 11.70 s
[Task 22/25] Current/Best: 15.87/ 20.87 GFLOPS | Progress: (20/20) | 16.53 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 15.06/ 19.39 GFLOPS | Progress: (4/20) | 3.46 s
[Task 23/25] Current/Best: 11.52/ 19.39 GFLOPS | Progress: (8/20) | 9.36 s
[Task 23/25] Current/Best: 12.34/ 19.39 GFLOPS | Progress: (12/20) | 14.41 s
[Task 23/25] Current/Best: 10.25/ 19.39 GFLOPS | Progress: (16/20) | 16.55 s
[Task 23/25] Current/Best: 8.72/ 22.87 GFLOPS | Progress: (20/20) | 18.90 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.71/ 6.61 GFLOPS | Progress: (4/20) | 12.29 s
[Task 24/25] Current/Best: 10.08/ 10.41 GFLOPS | Progress: (8/20) | 18.05 s
[Task 24/25] Current/Best: 2.29/ 10.41 GFLOPS | Progress: (12/20) | 28.74 s
[Task 24/25] Current/Best: 3.16/ 10.41 GFLOPS | Progress: (16/20) | 39.49 s
[Task 24/25] Current/Best: 3.59/ 10.41 GFLOPS | Progress: (20/20) | 50.22 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 3.58/ 9.62 GFLOPS | Progress: (4/20) | 3.44 s
[Task 25/25] Current/Best: 9.34/ 9.62 GFLOPS | Progress: (8/20) | 14.13 s
[Task 25/25] Current/Best: 5.71/ 9.62 GFLOPS | Progress: (12/20) | 25.72 s
[Task 25/25] Current/Best: 1.53/ 9.62 GFLOPS | Progress: (16/20) | 29.68 s
[Task 25/25] Current/Best: 9.41/ 9.62 GFLOPS | Progress: (20/20) | 39.74 s
@@ -730,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 420.548323229998, 'median': 419.18809934999217, 'std': 2.3935357569023203}
- unoptimized: {'mean': 513.6498611600007, 'median': 512.9932505999989, 'std': 2.8798782377045864}
+ optimized: {'mean': 402.2415456800013, 'median': 402.3510191499895, 'std': 1.4102802177687321}
+ unoptimized: {'mean': 514.4685151600027, 'median': 514.7692598500043, 'std': 2.0755005781498563}
@@ -754,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 49.911 seconds)
+ **Total running time of the script:** ( 10 minutes 43.439 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 059d3ff1f9..bc19b003d9 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
- 1.255e-07 secs/op
+ 1.285e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 39019f1b6e..529edebcf1 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xd74ba80)), stage(b, placeholder(b, 0x104ed9c0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x24838610)), stage(b, placeholder(b, 0x21539400)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index afe37519b2..7ca8437eef 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**14:13.496** total execution time for **tutorial** files:
+**14:17.695** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:49.911 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:43.439 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:20.474 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:32.627 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.203 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.295 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.964 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.655 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:26.731 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.535 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.204 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.147 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.823 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.816 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.176 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.170 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.009 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.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 91edb03260..cb7edd4d71 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -448,7 +448,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000032
+ vector: 0.000025
@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, [n: int32], [stride: int32], type="auto"),
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.413470000301459e-06 1.0
- naive 6.7092e-06 0.9050013016478355
- parallel 7.0004e-06 0.9442811530518553
- vector 3.1934600000000004e-05 4.3076454074409725
+ numpy 7.14468999831297e-06 1.0
+ naive 6.6874e-06 0.9359958236927078
+ parallel 6.958000000000001e-06 0.9738701051610286
+ vector 2.4631000000000002e-05 3.4474553837627613
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018936
+ Numpy running time: 0.018779
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.360323
+ none: 3.351026
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.287523
+ blocking: 0.308305
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.327672
+ vectorization: 0.340001
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118925
+ loop permutation: 0.116010
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.110206
+ array packing: 0.108277
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111587
+ block caching: 0.110562
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.147741
+ parallelization: 0.146057
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3603228951999995 1.0
- blocking 0.2875230125 0.08556410245893564
- vectorization 0.3276717984 0.09751199769166756
- loop permutation 0.1189248131 0.0353908885571313
- array packing 0.11020558619999998 0.03279612990686741
- block caching 0.1115868118 0.033207169453683884
- parallelization 0.1477406443 0.04396620470938606
+ none 3.3510256456 1.0
+ blocking 0.30830460029999995 0.09200305605085816
+ vectorization 0.3400014722 0.10146191290610754
+ loop permutation 0.11600963909999999 0.034619143918616146
+ array packing 0.10827707689999999 0.03231162287348386
+ block caching 0.1105616469 0.03299337534022482
+ parallelization 0.1460566826 0.043585665419116355
@@ -1654,7 +1654,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.203 seconds)
+ **Total running time of the script:** ( 1 minutes 0.295 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 644c405c3f..e97b6eb9ac 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-3168e612c7ebaa99993c693fb33a6c137e510950
+9e7920b58107e55f1d05fcac4f75de87f94341e6
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 939a155471..0ebc7ce5d1 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -579,7 +579,7 @@ 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 9.583 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.642 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 f384adb58c..10bcf2f272 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -500,7 +500,7 @@ 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 945ms/step
+1/1 [==============================] - 1s 938ms/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 3dee241cc2..6434768a87 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -434,7 +434,7 @@ 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.zipe5d2a290-443f-4a47-9f68-820649f70631 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.zipf0ebeb96-5bcb-4004-8884-55b7ded0524e 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 b00c1bb577..474c4b4540 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -442,13 +442,14 @@ 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, 51.1MB/s]
- 27%|##7 | 11.2M/41.5M [00:00<00:00, 48.6MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 39.7MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 44.3MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 53.7MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 53.2MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 50.5MB/s]
+ 15%|#5 | 6.39M/41.5M [00:00<00:00, 67.0MB/s]
+ 31%|### | 12.8M/41.5M [00:00<00:00, 56.3MB/s]
+ 44%|####4 | 18.3M/41.5M [00:00<00:00, 44.3MB/s]
+ 55%|#####4 | 22.7M/41.5M [00:00<00:00, 41.8MB/s]
+ 67%|######7 | 27.9M/41.5M [00:00<00:00, 45.4MB/s]
+ 78%|#######8 | 32.4M/41.5M [00:00<00:00, 46.1MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00<00:00, 51.2MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 50.2MB/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 35ae63d814..73be4a670a 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -425,12 +425,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 77.2MB/s]
- 34%|###4 | 15.4M/44.7M [00:00<00:00, 70.2MB/s]
- 49%|####9 | 22.1M/44.7M [00:00<00:00, 67.0MB/s]
- 64%|######3 | 28.5M/44.7M [00:00<00:00, 64.4MB/s]
- 86%|########5 | 38.3M/44.7M [00:00<00:00, 77.3MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 66.7MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 75.1MB/s]
+ 37%|###6 | 16.4M/44.7M [00:00<00:00, 82.4MB/s]
+ 72%|#######1 | 32.0M/44.7M [00:00<00:00, 99.2MB/s]
+ 99%|#########8| 44.2M/44.7M [00:00<00:00, 102MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 97.8MB/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 0710417155..4a850c3a8d 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -639,7 +639,7 @@ 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 12.157 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.531 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 81d0e73947..3068d36749 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>05:43.877</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:40.209</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -343,43 +343,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:12.157</p></td>
+<td><p>01:11.531</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:09.583</p></td>
+<td><p>01:08.642</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:46.953</p></td>
+<td><p>00:46.801</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>00:32.399</p></td>
+<td><p>00:32.128</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.047</p></td>
+<td><p>00:28.857</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>00:26.488</p></td>
+<td><p>00:26.447</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.338</p></td>
+<td><p>00:24.536</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.167</p></td>
+<td><p>00:21.917</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>00:17.304</p></td>
+<td><p>00:16.946</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>00:02.442</p></td>
+<td><p>00:02.403</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index da3344b124..288faa4393 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -913,7 +913,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2686.8099 2686.6009 2690.7188 2685.4666 1.4030
+ 2687.3950 2686.7537 2692.0654 2685.4634 1.9608
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index a5e4b2c246..e58871b61d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -655,7 +655,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0373 15.6872 16.9190 15.6455 0.4964
+ 16.3516 16.3789 17.0786 15.8099 0.4488
</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 e704c6844d..430e18f9d8 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -447,25 +447,24 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 8%|7 | 12.9M/170M [00:00<00:01, 136MB/s]
- 15%|#5 | 25.9M/170M [00:00<00:02, 71.8MB/s]
- 20%|## | 34.2M/170M [00:00<00:01, 75.9MB/s]
- 25%|##4 | 42.5M/170M [00:00<00:01, 67.8MB/s]
- 29%|##9 | 49.5M/170M [00:00<00:01, 64.8MB/s]
- 34%|###3 | 57.6M/170M [00:00<00:01, 69.9MB/s]
- 38%|###8 | 64.6M/170M [00:00<00:01, 69.3MB/s]
- 45%|####4 | 76.3M/170M [00:01<00:01, 84.2MB/s]
- 50%|####9 | 84.8M/170M [00:01<00:01, 74.0MB/s]
- 56%|#####5 | 94.4M/170M [00:01<00:00, 81.1MB/s]
- 60%|###### | 103M/170M [00:01<00:00, 75.8MB/s]
- 66%|######5 | 112M/170M [00:01<00:00, 70.5MB/s]
- 73%|#######3 | 124M/170M [00:01<00:00, 84.8MB/s]
- 79%|#######9 | 134M/170M [00:01<00:00, 86.6MB/s]
- 84%|########4 | 143M/170M [00:01<00:00, 77.9MB/s]
- 89%|########8 | 151M/170M [00:02<00:00, 68.3MB/s]
- 94%|#########3| 159M/170M [00:02<00:00, 72.1MB/s]
- 98%|#########7| 166M/170M [00:02<00:00, 64.5MB/s]
-100%|##########| 170M/170M [00:02<00:00, 73.6MB/s]
+ 6%|5 | 10.1M/170M [00:00<00:01, 95.8MB/s]
+ 13%|#3 | 22.6M/170M [00:00<00:01, 116MB/s]
+ 20%|#9 | 33.8M/170M [00:00<00:01, 90.5MB/s]
+ 28%|##7 | 47.0M/170M [00:00<00:01, 106MB/s]
+ 34%|###4 | 57.8M/170M [00:00<00:01, 78.5MB/s]
+ 42%|####2 | 72.0M/170M [00:00<00:01, 85.7MB/s]
+ 48%|####7 | 81.0M/170M [00:00<00:01, 80.1MB/s]
+ 52%|#####2 | 89.1M/170M [00:01<00:01, 80.3MB/s]
+ 57%|#####7 | 97.1M/170M [00:01<00:00, 77.7MB/s]
+ 62%|######1 | 105M/170M [00:01<00:00, 74.3MB/s]
+ 67%|######6 | 113M/170M [00:01<00:00, 78.4MB/s]
+ 72%|#######2 | 123M/170M [00:01<00:00, 84.3MB/s]
+ 79%|#######9 | 134M/170M [00:01<00:00, 87.6MB/s]
+ 85%|########4 | 144M/170M [00:01<00:00, 83.1MB/s]
+ 90%|######### | 153M/170M [00:01<00:00, 86.0MB/s]
+ 95%|#########4| 161M/170M [00:02<00:00, 83.2MB/s]
+100%|#########9| 169M/170M [00:02<00:00, 77.3MB/s]
+100%|##########| 170M/170M [00:02<00:00, 83.4MB/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=& [...]
@@ -563,7 +562,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 16.740 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 14.882 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 e706c365f2..a07eb8d991 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -491,8 +491,8 @@ 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]
- 73%|#######2 | 9.84M/13.6M [00:00<00:00, 103MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 112MB/s]
+ 95%|#########4| 12.9M/13.6M [00:00<00:00, 135MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 132MB/s]
</pre></div>
</div>
</div>
@@ -583,7 +583,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2997 90.2074 93.9229 90.0076 0.4177
+ 90.2519 90.1644 94.6986 90.0153 0.4671
</pre></div>
</div>
<div class="admonition note">
@@ -622,7 +622,7 @@ 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 6.906 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.957 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 f39da32854..75b9663be8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -576,7 +576,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.3177 119.2019 122.6607 118.5333 0.6330
+ 119.7810 119.7477 120.9401 118.8872 0.4089
</pre></div>
</div>
<div class="admonition note">
@@ -604,7 +604,7 @@ 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 22.560 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.145 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 67ed9eb0af..df71ef9372 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -514,7 +514,7 @@ 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 24.370 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.326 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 7583fa1361..e9015a3a26 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -456,23 +456,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5783/132723 [00:00<00:02, 57823.02KB/s]
- 10%|# | 13741/132723 [00:00<00:01, 70615.00KB/s]
- 16%|#6 | 21741/132723 [00:00<00:01, 74895.15KB/s]
- 22%|##2 | 29806/132723 [00:00<00:01, 77164.98KB/s]
- 28%|##8 | 37761/132723 [00:00<00:01, 78022.19KB/s]
- 35%|###4 | 45802/132723 [00:00<00:01, 78830.88KB/s]
- 41%|#### | 53779/132723 [00:00<00:00, 79135.62KB/s]
- 47%|####6 | 61837/132723 [00:00<00:00, 79592.30KB/s]
- 53%|#####2 | 69832/132723 [00:00<00:00, 79701.34KB/s]
- 59%|#####8 | 77803/132723 [00:01<00:00, 79647.24KB/s]
- 65%|######4 | 85784/132723 [00:01<00:00, 79693.73KB/s]
- 71%|####### | 93764/132723 [00:01<00:00, 79717.98KB/s]
- 77%|#######6 | 101748/132723 [00:01<00:00, 79749.43KB/s]
- 83%|########2 | 109746/132723 [00:01<00:00, 79816.31KB/s]
- 89%|########8 | 117728/132723 [00:01<00:00, 79542.04KB/s]
- 95%|#########4| 125715/132723 [00:01<00:00, 79638.13KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 78462.69KB/s]
+ 5%|4 | 6036/132723 [00:00<00:02, 60355.88KB/s]
+ 11%|#1 | 14673/132723 [00:00<00:01, 75655.37KB/s]
+ 18%|#7 | 23323/132723 [00:00<00:01, 80603.62KB/s]
+ 24%|##4 | 32033/132723 [00:00<00:01, 83165.65KB/s]
+ 30%|### | 40350/132723 [00:00<00:01, 76549.95KB/s]
+ 37%|###6 | 48930/132723 [00:00<00:01, 79522.29KB/s]
+ 43%|####3 | 57627/132723 [00:00<00:00, 81863.00KB/s]
+ 50%|####9 | 66298/132723 [00:00<00:00, 83365.51KB/s]
+ 57%|#####6 | 75034/132723 [00:00<00:00, 84590.58KB/s]
+ 63%|######3 | 83690/132723 [00:01<00:00, 85188.82KB/s]
+ 70%|######9 | 92425/132723 [00:01<00:00, 85840.23KB/s]
+ 76%|#######6 | 101156/132723 [00:01<00:00, 86283.43KB/s]
+ 83%|########2 | 109874/132723 [00:01<00:00, 86550.86KB/s]
+ 89%|########9 | 118538/132723 [00:01<00:00, 85820.56KB/s]
+ 96%|#########5| 127192/132723 [00:01<00:00, 86032.97KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83377.23KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -511,7 +510,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 7.323 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 6.405 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 f6d638d3de..ec34939c0c 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -334,7 +334,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:36.965</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:35.961</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -343,43 +343,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:16.740</p></td>
+<td><p>03:14.882</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:07.323</p></td>
+<td><p>03:06.405</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>02:22.560</p></td>
+<td><p>02:23.145</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>01:24.370</p></td>
+<td><p>01:27.326</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:06.906</p></td>
+<td><p>01:05.957</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:53.355</p></td>
+<td><p>00:53.142</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:35.640</p></td>
+<td><p>00:35.542</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.266</p></td>
+<td><p>00:24.841</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.799</p></td>
+<td><p>00:24.715</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index d656d4d090..66e8de81bf 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -615,7 +615,7 @@ 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.zipcd8aa24e-03e3-4932-bceb-dbd0f76b4209 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.zip35890870-a81b-4c87-a19c-647bdfab48ac 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 74c1bb5b1c..1a8db1fd23 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>00:47.495</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:47.776</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -343,19 +343,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:43.998</p></td>
+<td><p>00:44.299</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>00:02.453</p></td>
+<td><p>00:02.432</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.036</p></td>
+<td><p>00:01.037</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 859fdf3c55..a24eefd8e0 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -519,10 +519,10 @@ 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: 7171us [7171us] (46.41%; 46.41%)
-FoldScaleAxis: 8279us [6us] (53.59%; 53.59%)
- FoldConstant: 8272us [1704us] (53.54%; 99.92%)
- InferType: 6568us [6568us] (42.51%; 79.40%)
+InferType: 7420us [7420us] (46.85%; 46.85%)
+FoldScaleAxis: 8418us [6us] (53.15%; 53.15%)
+ FoldConstant: 8412us [1738us] (53.11%; 99.93%)
+ InferType: 6674us [6674us] (42.14%; 79.34%)
</pre></div>
</div>
</div>
@@ -544,10 +544,10 @@ 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: 6624us [6624us] (44.75%; 44.75%)
-FoldScaleAxis: 8177us [5us] (55.25%; 55.25%)
- FoldConstant: 8173us [1690us] (55.21%; 99.94%)
- InferType: 6483us [6483us] (43.80%; 79.33%)
+InferType: 6597us [6597us] (44.96%; 44.96%)
+FoldScaleAxis: 8078us [5us] (55.04%; 55.04%)
+ FoldConstant: 8073us [1668us] (55.01%; 99.94%)
+ InferType: 6405us [6405us] (43.65%; 79.34%)
</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 904b30550b..429b9389a7 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -571,7 +571,7 @@ 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: 52.373729 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.171905 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 49b07f9964..dca478a65c 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -908,7 +908,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.379773 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.376282 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 6412eabf42..3b14951b1e 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -468,8 +468,8 @@ 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: 0.018386
-Baseline: 3.365053
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018521
+Baseline: 3.341563
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -528,7 +528,7 @@ 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: 0.305447
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300738
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ 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: 0.343218
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337540
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -654,7 +654,7 @@ 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: 0.114950
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116263
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -736,7 +736,7 @@ 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: 0.108336
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109464
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -821,7 +821,7 @@ 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: 0.111308
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110901
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -910,7 +910,7 @@ 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: 0.147381
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146968
</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 c4348b7872..1f238366f5 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -334,7 +334,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.970</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.683</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -343,15 +343,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.299</p></td>
+<td><p>00:32.127</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>00:01.554</p></td>
+<td><p>00:01.505</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>00:01.118</p></td>
+<td><p>00:01.051</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 758122873f..8d08b21d45 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -334,7 +334,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:06.235</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:50.250</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -343,27 +343,27 @@
</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>05:41.941</p></td>
+<td><p>05:26.361</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>01:31.656</p></td>
+<td><p>01:31.708</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:02.015</p></td>
+<td><p>01:02.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:27.445</p></td>
+<td><p>00:26.928</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.057</p></td>
+<td><p>00:12.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.121</p></td>
+<td><p>00:11.224</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 e560fb9690..7b53a88c90 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
@@ -498,11 +498,11 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), 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" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [28], [], scope="local")[0] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local")[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -518,890 +518,80 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[13] = 0f32
conv2d_nchw_1[14] = 0f32
conv2d_nchw_1[15] = 0f32
- conv2d_nchw_1[16] = 0f32
- conv2d_nchw_1[17] = 0f32
- conv2d_nchw_1[18] = 0f32
- conv2d_nchw_1[19] = 0f32
- conv2d_nchw_1[20] = 0f32
- conv2d_nchw_1[21] = 0f32
- conv2d_nchw_1[22] = 0f32
- conv2d_nchw_1[23] = 0f32
- conv2d_nchw_1[24] = 0f32
- conv2d_nchw_1[25] = 0f32
- conv2d_nchw_1[26] = 0f32
- conv2d_nchw_1[27] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
+ 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" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1064), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1288), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1400), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1168)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1624), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1736), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1848), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[((((((blockIdx.x*147456) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 96)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[(threadIdx.x_1*6)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((rc.outer.outer*392) + (floordiv(( [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*2), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 4)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_ [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 5)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*2) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data_3[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1 [...]
+ }
}
- for (rc.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 96)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 99)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 102)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 108)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 111)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 114)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 117)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 192)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 288)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 195)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 291)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 198)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 294)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 201)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 297)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 204)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 300)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 207)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 303)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 210)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 306)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 213)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 97)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 100)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 103)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 109)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 112)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 115)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 118)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 193)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 289)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 196)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 292)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 199)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 295)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 202)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 298)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 205)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 301)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 208)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 304)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 211)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 379)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 307)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 214)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 442)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 310)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 98)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 101)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 104)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 107)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 110)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 113)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 116)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 119)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 194)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 290)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 197)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 293)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 200)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 296)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 203)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 299)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 206)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 302)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 209)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 318)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 319)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 320)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 321)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 305)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 212)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 380)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 381)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 382)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 383)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 384)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 308)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 215)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 443)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 444)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 445)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 446)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 447)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floormod(threadIdx.x, 7)*9)) + 449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*384) + (rc.outer.inner*24)) + 311)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((blockIdx.x*147456) + (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" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 4), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 294), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 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" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 490), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 10), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 82), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 686), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 14), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (rx.outer.inner: int32, 0, 3) {
+ for (ff.outer.inner: int32, 0, 2) {
+ for (rc.inner: int32, 0, 4) {
+ let cse_var_10: int32 = (ff.outer.inner*8)
+ let cse_var_9: int32 = (cse_var_10 + 7)
+ let cse_var_8: int32 = (cse_var_10 + 6)
+ let cse_var_7: int32 = (cse_var_10 + 5)
+ let cse_var_6: int32 = (cse_var_10 + 4)
+ let cse_var_5: int32 = (cse_var_10 + 3)
+ let cse_var_4: int32 = (cse_var_10 + 2)
+ let cse_var_3: int32 = (cse_var_10 + 1)
+ {
+ conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 48)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 96)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 120)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*192)) + (rc.outer.inner*12)) + (rc.inner*3)) + rx.outer.inner) + 168)]))
+ }
+ }
+ }
+ }
}
}
}
}
- for (i1.inner: int32, 0, 4) {
- for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 16) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*784)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*16)) + i1.inner)]), 0f32)
}
}
}
@@ -1438,7 +628,7 @@ 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: 0.276 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.322 ms
</pre></div>
</div>
</div>
@@ -1467,20 +657,20 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=8)
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=8)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+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=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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)
@@ -1489,14 +679,14 @@ s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, 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=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1516,14 +706,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+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=98)
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=6)
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=56)
+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=98)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1541,10 +731,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[504];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1561,795 +751,58 @@ extern "C" __global__ void __launch_bounds__(56) default_function_kern
conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[14] = 0.000000e+00f;
conv2d_nchw[15] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
- conv2d_nchw[26] = 0.000000e+00f;
- conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ 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)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1400)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1168)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1624)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1848) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[(((int)threadIdx.x) * 6)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000 [...]
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.00 [...]
+ }
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000 [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((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) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 2) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 4) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 294) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 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) + 490)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 490) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 10) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 82) {
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 686) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 14) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 192)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 288)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 195)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 291)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 198)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 294)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 201)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 297)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 204)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 300)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 207)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 303)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 210)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 306)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 213)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 193)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 289)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 196)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 292)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 199)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 295)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 202)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 298)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 205)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 301)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 208)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 304)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 211)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 307)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 214)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 310)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 119)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 194)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 290)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 197)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 293)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 200)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 296)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 203)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 299)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 206)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 302)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 209)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 318)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 319)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 320)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 321)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 305)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 212)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 381)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 382)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 383)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 384)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 308)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 215)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 444)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 445)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 446)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 447)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) % 7) * 9)) + 449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 384) + (rc_outer_inner * 24)) + 311)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ conv2d_nchw[(ff_outer_inner * 8)] = (conv2d_nchw[(ff_outer_inner * 8)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 1)] = (conv2d_nchw[((ff_outer_inner * 8) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 24)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 2)] = (conv2d_nchw[((ff_outer_inner * 8) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 48)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 3)] = (conv2d_nchw[((ff_outer_inner * 8) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 4)] = (conv2d_nchw[((ff_outer_inner * 8) + 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 96)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 5)] = (conv2d_nchw[((ff_outer_inner * 8) + 5)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 120)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 6)] = (conv2d_nchw[((ff_outer_inner * 8) + 6)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[((ff_outer_inner * 8) + 7)] = (conv2d_nchw[((ff_outer_inner * 8) + 7)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 12)) + (rc_inner * 3)) + rx_outer_inner) + 168)]));
+ }
+ }
+ }
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 784)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 16)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -2386,7 +839,7 @@ 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 41.941 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 26.361 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 9c0ce2bc7b..773dfa4261 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -909,7 +909,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9061 7.9022 7.9147 7.9013 0.0061
+ 7.9069 7.9065 7.9131 7.9012 0.0049
</pre></div>
</div>
</div>
@@ -931,7 +931,7 @@ 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 2.015 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.008 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 286110be49..65e404c76c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -928,7 +928,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.7608 757.8931 760.0372 752.3521 3.2380
+ 751.7627 751.8361 753.1049 750.3471 1.1271
</pre></div>
</div>
</div>
@@ -950,7 +950,7 @@ 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 31.656 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.708 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 b1eb7178ba..e80dcead99 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -626,28 +626,29 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 2) {
for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ compute_4: Buffer(compute_3, float32, [256], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 16) {
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 2) {
for (j: int32, 0, 16) {
- if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
- compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*4096) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_2, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -685,7 +686,7 @@ 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: 1.531 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.182 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 7b4a8e373a..67da1d4f29 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>00:27.684</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:53.819</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -343,11 +343,11 @@
</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>00:27.649</p></td>
+<td><p>00:53.783</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 2347ac3c6a..a5df16249d 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -683,8 +683,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10064893
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8765017
+No: 2 GFLOPS: 6.92/6.92 result: MeasureResult(costs=(0.033444641,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2071523666381836, timestamp=1670534228.202493) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1064021
+No: 3 GFLOPS: 0.00/6.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -806,8 +807,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7834570
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5786950
+No: 4 GFLOPS: 0.00/6.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -929,8 +930,26 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1324824
-No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2077139
+No: 5 GFLOPS: 0.00/6.92 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, 1, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4189440
+No: 6 GFLOPS: 0.00/6.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1052,8 +1071,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3054807
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6627620
+No: 7 GFLOPS: 66.16/66.16 result: MeasureResult(costs=(0.003499268333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.989178419113159, timestamp=1670534242.2051907) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9008441
+No: 8 GFLOPS: 0.00/66.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1175,8 +1195,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7972071
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,382858
+No: 9 GFLOPS: 0.00/66.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1298,9 +1318,11 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,852430
-No: 7 GFLOPS: 79.66/79.66 result: MeasureResult(costs=(0.002906020725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5092182159423828, timestamp=1670533421.405791) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4489994
-No: 8 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('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', 1)],None,5925668
+No: 10 GFLOPS: 113.29/113.29 result: MeasureResult(costs=(0.002043401755102041,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6215996742248535, timestamp=1670534246.9681785) [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9392725
+No: 11 GFLOPS: 246.78/246.78 result: MeasureResult(costs=(0.0009380924796747967,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.99544095993042, timestamp=1670534247.6343) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3588662
+No: 12 GFLOPS: 143.26/246.78 result: MeasureResult(costs=(0.0016159303709677422,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.2158825397491455, timestamp=1670534248.3304582) [('tile_f', [-1, 1, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3886915
+No: 13 GFLOPS: 0.00/246.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1422,8 +1444,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7330674
-No: 9 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1489074
+No: 14 GFLOPS: 312.76/312.76 result: MeasureResult(costs=(0.0007401817801418438,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6705849170684814, timestamp=1670534250.1962533) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2226544
+No: 15 GFLOPS: 0.00/312.76 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1545,8 +1568,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3206099
-No: 10 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1695743
+No: 16 GFLOPS: 0.00/312.76 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1668,778 +1691,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1797223
-No: 11 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fdf16a72fa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1617
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8169256
-No: 12 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6062590
-No: 13 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7761691
-No: 14 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6687879
-No: 15 GFLOPS: 0.00/79.66 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10222511
-No: 16 GFLOPS: 274.36/274.36 result: MeasureResult(costs=(0.0008437847279999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.343325138092041, timestamp=1670533428.3862648) [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3559233
-No: 17 GFLOPS: 0.00/274.36 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 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:1749
- 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:1693
- 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:1617
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6517092
-No: 18 GFLOPS: 246.20/274.36 result: MeasureResult(costs=(0.0009403128130841122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9367525577545166, timestamp=1670533429.5178611) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5658480
-No: 19 GFLOPS: 0.00/274.36 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3052515
+No: 17 GFLOPS: 84.21/312.76 result: MeasureResult(costs=(0.002749206904761905,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6787645816802979, timestamp=1670534258.3552167) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7005518
+No: 18 GFLOPS: 0.00/312.76 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2561,8 +1815,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9931119
-No: 20 GFLOPS: 0.00/274.36 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7134889
+No: 19 GFLOPS: 500.65/500.65 result: MeasureResult(costs=(0.00046240396017699115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.637235641479492, timestamp=1670534259.0428703) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10360681
+No: 20 GFLOPS: 0.00/500.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2684,7 +1939,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6664114
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1059350
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2723,9 +1978,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3559233
+[('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10360681
Finish loading 20 records
-Time cost of this operator: 0.001178
+Time cost of this operator: 0.000838
</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 25b93ea092..8507f6cd20 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -592,10 +592,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.5 98.715 (1, 2, 10, 10, 3) 2 1 [311.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.069 0.973 (1, 6, 10, 10) 1 1 [3.069]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.986 0.312 (1, 1, 10, 10, 3) 1 1 [0.986]
-Total_time - 315.555 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.3 98.734 (1, 2, 10, 10, 3) 2 1 [312.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.955 (1, 6, 10, 10) 1 1 [3.021]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.311 (1, 1, 10, 10, 3) 1 1 [0.984]
+Total_time - 316.305 - - - - -
</pre></div>
</div>
</div>
@@ -647,10 +647,10 @@ 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 137.0 98.0 (1, 6, 10, 10, 1) 2 1 [137.0]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.832 1.31 (1, 6, 10, 10) 1 1 [1.832]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.689 (1, 1, 10, 10, 3) 1 1 [0.964]
-Total_time - 139.795 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 105.3 97.574 (1, 6, 10, 10, 1) 2 1 [105.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.778 1.648 (1, 6, 10, 10) 1 1 [1.778]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.778 (1, 3, 10, 10, 1) 1 1 [0.84]
+Total_time - 107.918 - - - - -
</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 df5232b172..9b3485c9fd 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -434,7 +434,7 @@ 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]
-100%|##########| 3.42M/3.42M [00:00<00:00, 42.6MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 43.9MB/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.
@@ -558,7 +558,7 @@ 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 3.863 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.819 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 95be80de73..6c3d32e39a 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -524,7 +524,7 @@ 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/tmpt2fbb_2z/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpufmxekuo/images/random'
</pre></div>
</div>
</div>
@@ -584,8 +584,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpt2fbb_2z/images/target contains 8144 images
-/tmp/tmpt2fbb_2z/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpufmxekuo/images/target contains 8144 images
+/tmp/tmpufmxekuo/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -697,13 +697,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2308 - accuracy: 0.9210 - val_loss: 0.1362 - val_accuracy: 0.9539 - 47s/epoch - 142ms/step
+328/328 - 47s - loss: 0.2660 - accuracy: 0.9131 - val_loss: 0.1781 - val_accuracy: 0.9456 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1019 - accuracy: 0.9625 - val_loss: 0.1074 - val_accuracy: 0.9641 - 43s/epoch - 132ms/step
+328/328 - 44s - loss: 0.1013 - accuracy: 0.9647 - val_loss: 0.1111 - val_accuracy: 0.9622 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0687 - accuracy: 0.9742 - val_loss: 0.1171 - val_accuracy: 0.9660 - 43s/epoch - 131ms/step
+328/328 - 44s - loss: 0.0703 - accuracy: 0.9748 - val_loss: 0.1128 - val_accuracy: 0.9664 - 44s/epoch - 133ms/step
-<keras.callbacks.History object at 0x7ff88a5d6910>
+<keras.callbacks.History object at 0x7f72fc8a6c10>
</pre></div>
</div>
</div>
@@ -965,7 +965,7 @@ 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 23.544 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 19.202 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 1a011aeaf8..5436988e19 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -334,7 +334,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:29.326</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:24.816</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -343,23 +343,23 @@
</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>04:23.544</p></td>
+<td><p>04:19.202</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:03.863</p></td>
+<td><p>01:03.819</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>00:50.271</p></td>
+<td><p>00:50.181</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>00:07.869</p></td>
+<td><p>00:07.817</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>00:03.777</p></td>
+<td><p>00:03.794</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 af97bf5be7..b595703186 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -334,7 +334,7 @@
<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>00:44.303</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.321</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -343,15 +343,15 @@
</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>00:32.500</p></td>
+<td><p>00:32.414</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.244</p></td>
+<td><p>00:10.146</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>00:01.553</p></td>
+<td><p>00:01.754</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 1761ebe154..b4c43c9b18 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -529,7 +529,7 @@ 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 0x7ff8e82d0170>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f72f3422050>
</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 405c73b6c8..123a86eb85 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -334,7 +334,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:06.796</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.969</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -343,11 +343,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.318</p></td>
+<td><p>00:05.457</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>00:01.129</p></td>
+<td><p>00:01.162</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>
@@ -355,11 +355,11 @@
<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>00:00.558</p></td>
+<td><p>00:00.556</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>00:00.114</p></td>
+<td><p>00:00.115</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>
@@ -367,11 +367,11 @@
<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>00:00.028</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>00:00.024</p></td>
+<td><p>00:00.023</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 887db90f34..54649a93a6 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -580,7 +580,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpb1xpvrmc/input0.cc'\nsource_filename = \"/tmp/tmpb1xpvrmc/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/tmp2dgve0xt/input0.cc'\nsource_filename = \"/tmp/tmp2dgve0xt/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 8d4004f4e4..705ee620df 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,7 +229,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index d354b9595a..d9ebae9893 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1609,7 +1609,7 @@ 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>
@@ -1893,7 +1893,7 @@ 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 d72de2edc8..75ceba45bc 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/3168e612c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 69ec018dbf..89d2e82952 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/3168e612c/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 75a61d84f8..a1ab54fa27 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/3168e612c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 2d30453af8..5d660d92ed 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/3168e612c/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 090834f37b..71fdf613f0 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/3168e612c/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 3df312e21e..3b274e81ff 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/3168e612c/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 2f98101c79..20fade6ece 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/3168e612c/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 67d85cc94d..bc02037cc4 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/3168e612c/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 d727b84fad..9d6f47e95d 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/3168e612c/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 236d543231..b07cca7c0f 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/3168e612c/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 9470c72068..7fc06a0033 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/3168e612c/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 d73aa064f5..18d04f1d73 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/3168e612c/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 35b1b317cc..4ed2f7922c 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/3168e612c/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 5dc0c17916..4310b347c3 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/3168e612c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 926e3424c5..6a9cabf75f 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/3168e612c/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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 6b7cd2e0cf..67ee3960da 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/3168e612c/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/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/3168e612c/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e7920b58/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
... 1593 lines suppressed ...