You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/01/25 01:05:42 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@fd3f8035c94b31dbdbcce97864b1362ad254e4d1)
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 ea61ab9a48 deploying docs (apache/tvm@fd3f8035c94b31dbdbcce97864b1362ad254e4d1)
ea61ab9a48 is described below
commit ea61ab9a484c1656e41c97a8f221c87f21cd9a0b
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jan 25 01:05:35 2023 +0000
deploying docs (apache/tvm@fd3f8035c94b31dbdbcce97864b1362ad254e4d1)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 332942 -> 344037 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23901 -> 24159 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2342 ++++++++++++--------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 78 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 316 +--
.../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 | 16 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 47 +-
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 | 42 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2342 ++++++++++++--------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 78 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 316 +--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 16 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 10 +-
.../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 | 272 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
130 files changed, 3794 insertions(+), 3319 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 52fc7b9506..457bf652be 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 7c8ae2aa15..13642b47f1 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 78c06f89b4..0fa3d002bb 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 17.043 seconds)
+ **Total running time of the script:** ( 1 minutes 21.544 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 3aacb637c7..91bdc62360 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 913ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 1s/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 c7524d7d93..45907bbb62 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipcfa713df-1c84-4f10-ab81-733f5d3f2f4f from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipbb3a71ff-efef-4c42-8851-fa104a54ca26 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 d150280980..465c52a5b1 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 69.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 68.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 62.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 68.3MB/s]
93%|#########3| 38.6M/41.5M [00:00<00:00, 53.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 58.6MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 39.4MB/s]
24%|##4 | 10.1M/41.5M [00:00<00:00, 38.0MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 41.9MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 39.8MB/s]
63%|######3 | 26.1M/41.5M [00:00<00:00, 32.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.4MB/s]
91%|#########1| 37.9M/41.5M [00:00<00:00, 43.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 36.8MB/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 ebe8e91e9f..198f731a38 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
15%|#4 | 6.60M/44.7M [00:00<00:00, 69.2MB/s]
36%|###5 | 15.9M/44.7M [00:00<00:00, 85.8MB/s]
68%|######7 | 30.3M/44.7M [00:00<00:00, 115MB/s]
92%|#########2| 41.3M/44.7M [00:00<00:00, 111MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 111MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
28%|##8 | 12.7M/44.7M [00:00<00:00, 133MB/s]
57%|#####6 | 25.4M/44.7M [00:00<00:00, 112MB/s]
81%|########1 | 36.2M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 108MB/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 d88bdf7036..38c29ee43e 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.287 seconds)
+ **Total running time of the script:** ( 1 minutes 24.907 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 cb368a39a6..a94fb5984c 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**06:18.324** total execution time for **how_to_compile_models** files:
+**06:39.827** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:20.287 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:24.907 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:17.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:21.544 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:51.560 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:54.673 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:34.920 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.635 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:30.693 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.544 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.628 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.625 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.575 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.952 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.011 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.675 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:20.928 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:21.549 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.678 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.725 | 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 38921ac1a0..b73ccf885c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -727,7 +727,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2760.6683 2760.2357 2763.2731 2758.6312 1.3020
+ 2754.4563 2753.5079 2761.9300 2752.2152 2.7651
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 95cfd7dbca..6a57fcf87e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2175 16.3352 16.6377 15.6647 0.3352
+ 16.5539 16.3444 17.2734 16.2081 0.3907
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 7ac18c4389..e34b9c5127 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
1%|1 | 2.05M/170M [00:00<00:10, 17.3MB/s]
5%|4 | 7.99M/170M [00:00<00:05, 32.6MB/s]
9%|9 | 16.0M/170M [00:00<00:03, 51.3MB/s]
13%|#3 | 22.3M/170M [00:00<00:02, 52.0MB/s]
18%|#7 | 30.3M/170M [00:00<00:02, 56.1MB/s]
23%|##3 | 39.2M/170M [00:00<00:02, 66.8MB/s]
27%|##6 | 45.8M/170M [00:00<00:02, 63.3MB/s]
31%|### | 52.0M/170M [00:01<00:02, 46.8MB/s]
37%|###6 | 62.2M/170M [00:01<00:01, 60.4MB/s]
41%|#### | 68.9M/170M [00:01<00:01, 56.6MB/s]
44%|####4 | 75.0M/170M [00:01<00:01, 55.8MB/s]
48%|####7 | 80.7M/170M [00:01<00:01, 48.6MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 53.7MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 55.2MB/s]
60%|#####9 | 102M/170M [00:02<00:01, 49.6MB/s]
63%|######2 | 106M/170M [00:02<00:01, 40.1MB/s]
66%|######5 | 112M/170M [00:02<00:01, 39.5MB/s]
71%|####### | 120M/170M [00:02<00:01, 49.2MB/s]
75%|#######4 | 127M/170M [00:02<00:00, 54.8MB/s]
78%|#######8 | 133M/170M [00:02<00:00, 54.3MB/s]
82%|########1 | 138M/170M [00:02<00:00, 54.6MB/s]
85%|########5 | 145M/170M [00:02<00:00, 57.2MB/s]
88%|########8 | 150M/170M [00:03<00:00, 47.3MB/s]
92%|#########1| 156M/170M [00:03<00:00, 49.5MB/s]
95%|#########4| 161M/170M [00:03<00:00, 45.6MB/s]
99%|#########8| 168M/170M [00:03<00:00, 50.8MB/s]
100%|##########| 170M/170M [00:03<00:00, 51.5MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 67.4MB/s]
14%|#4 | 24.0M/170M [00:00<00:01, 105MB/s]
20%|## | 34.0M/170M [00:00<00:01, 88.5MB/s]
28%|##8 | 48.0M/170M [00:00<00:01, 96.9MB/s]
34%|###3 | 57.3M/170M [00:00<00:01, 77.6MB/s]
39%|###9 | 66.6M/170M [00:00<00:01, 62.5MB/s]
44%|####3 | 74.1M/170M [00:01<00:01, 54.0MB/s]
48%|####8 | 82.1M/170M [00:01<00:01, 49.2MB/s]
54%|#####4 | 92.4M/170M [00:01<00:01, 60.4MB/s]
58%|#####8 | 99.0M/170M [00:01<00:01, 62.0MB/s]
62%|######2 | 106M/170M [00:01<00:01, 58.8MB/s]
67%|######7 | 114M/170M [00:01<00:00, 65.2MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 69.1MB/s]
77%|#######6 | 130M/170M [00:02<00:00, 73.8MB/s]
82%|########1 | 139M/170M [00:02<00:00, 64.7MB/s]
89%|########9 | 152M/170M [00:02<00:00, 71.1MB/s]
97%|#########7| 165M/170M [00:02<00:00, 86.2MB/s]
100%|##########| 170M/170M [00:02<00:00, 71.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 25.499 seconds)
+ **Total running time of the script:** ( 3 minutes 41.745 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 5d7877762c..d35d03bdef 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
47%|####7 | 6.38M/13.6M [00:00<00:00, 66.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 80.1MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
53%|#####3 | 7.21M/13.6M [00:00<00:00, 75.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 28.0MB/s]
@@ -409,7 +409,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2753 90.1511 95.2123 90.0251 0.6409
+ 90.4976 90.4145 91.1622 90.2699 0.1995
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.487 seconds)
+ **Total running time of the script:** ( 1 minutes 17.588 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 75ab387ca1..370878a073 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.8064 120.7170 123.9868 120.0433 0.5117
+ 120.9403 120.8275 124.1355 120.1951 0.4916
@@ -460,7 +460,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 30.980 seconds)
+ **Total running time of the script:** ( 2 minutes 30.066 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 0141231496..5db32eff5e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 40.079 seconds)
+ **Total running time of the script:** ( 1 minutes 53.447 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 abfc445b29..f3650c6fd6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
2%|2 | 2671/132723 [00:00<00:04, 26706.97KB/s]
6%|5 | 7941/132723 [00:00<00:02, 41994.18KB/s]
12%|#1 | 15553/132723 [00:00<00:02, 57571.13KB/s]
18%|#7 | 23521/132723 [00:00<00:01, 66295.02KB/s]
24%|##3 | 31552/132723 [00:00<00:01, 71345.50KB/s]
30%|##9 | 39465/132723 [00:00<00:01, 73987.47KB/s]
36%|###5 | 47515/132723 [00:00<00:01, 76115.14KB/s]
42%|####1 | 55724/132723 [00:00<00:00, 78015.82KB/s]
48%|####7 | 63526/132723 [00:00<00:01, 62257.87KB/s]
53%|#####3 | 70636/132723 [00:01<00:00, 64579.06KB/s]
59%|#####8 | 77946/132723 [00:01<00:00, 66902.63KB/s]
64%|######4 | 85079/132723 [00:01<00:00, 68143.72KB/s]
69%|######9 | 92105/132723 [00:01<00:00, 67725.12KB/s]
75%|#######4 | 99025/132723 [00:01<00:00, 60682.27KB/s]
79%|#######9 | 105318/132723 [00:01<00:00, 57615.21KB/s]
85%|########5 |
113138/132723 [00:01<00:00, 63054.67KB/s]
91%|#########1| 121148/132723 [00:01<00:00, 67722.64KB/s]
97%|#########7| 129144/132723 [00:01<00:00, 71163.28KB/s]
100%|##########| 132723/132723 [00:01<00:00, 66441.67KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 917/132723 [00:00<00:14, 9089.09KB/s]
2%|2 | 2761/132723 [00:00<00:09, 14244.02KB/s]
5%|4 | 6054/132723 [00:00<00:05, 22653.45KB/s]
8%|8 | 10872/132723 [00:00<00:03, 32642.13KB/s]
13%|#3 | 17849/132723 [00:00<00:02, 45949.23KB/s]
20%|#9 | 26338/132723 [00:00<00:01, 59136.72KB/s]
24%|##4 | 32268/132723 [00:00<00:01, 59169.23KB/s]
31%|### | 40814/132723 [00:00<00:01, 67521.31KB/s]
37%|###6 | 48944/132723 [00:00<00:01, 71821.07KB/s]
42%|####2 | 56133/132723 [00:01<00:01, 64463.19KB/s]
48%|####7 | 63696/132723 [00:01<00:01, 67622.68KB/s]
54%|#####3 | 71197/132723 [00:01<00:00, 69748.74KB/s]
59%|#####9 | 78737/132723 [00:01<00:00, 71386.12KB/s]
65%|######4 | 85951/132723 [00:01<00:00, 59053.82KB/s]
70%|####### | 93348/132723 [00:01<00:00, 62889.98KB/s]
76%|#######5 | 100
678/132723 [00:01<00:00, 65685.34KB/s]
82%|########1 | 108199/132723 [00:01<00:00, 68326.51KB/s]
87%|########7 | 115680/132723 [00:01<00:00, 70164.36KB/s]
93%|#########2| 122856/132723 [00:02<00:00, 68917.17KB/s]
98%|#########8| 130370/132723 [00:02<00:00, 70696.70KB/s]
100%|##########| 132723/132723 [00:02<00:00, 61632.46KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 33.266 seconds)
+ **Total running time of the script:** ( 3 minutes 46.028 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 fd836b337c..7c64f8fc8c 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
=================
-**14:53.085** total execution time for **how_to_deploy_models** files:
+**15:44.868** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:33.266 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:46.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:25.499 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:41.745 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.980 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.066 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:40.079 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:53.447 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:13.487 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:17.588 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.086 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:57.310 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:40.338 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.938 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.926 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.101 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.418 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.638 | 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 a4906f55f3..607abaad3d 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip503b1a7b-8a58-4993-ba83-e53a434e2c63 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip615ebc50-9255-4590-8c3a-4b2e64134aff 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 53fa9a1630..580be26aa7 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
=================
-**00:52.337** total execution time for **how_to_extend_tvm** files:
+**00:55.765** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:48.556 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:51.846 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.692 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.802 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.083 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.111 | 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 |
+-------------------------------------------------------------------------------------------------+-----------+--------+
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 cef4c7b09e..d493368442 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 20835us [20835us] (47.62%; 47.62%)
- FoldScaleAxis: 22922us [8us] (52.38%; 52.38%)
- FoldConstant: 22914us [1732us] (52.37%; 99.97%)
- InferType: 21182us [21182us] (48.41%; 92.44%)
+ InferType: 21196us [21196us] (48.34%; 48.34%)
+ FoldScaleAxis: 22654us [9us] (51.66%; 51.66%)
+ FoldConstant: 22645us [1771us] (51.64%; 99.96%)
+ InferType: 20874us [20874us] (47.60%; 92.18%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 20405us [20405us] (48.09%; 48.09%)
- FoldScaleAxis: 22029us [7us] (51.91%; 51.91%)
- FoldConstant: 22022us [1742us] (51.90%; 99.97%)
- InferType: 20280us [20280us] (47.79%; 92.09%)
+ InferType: 20944us [20944us] (48.07%; 48.07%)
+ FoldScaleAxis: 22628us [8us] (51.93%; 51.93%)
+ FoldConstant: 22620us [1819us] (51.91%; 99.97%)
+ InferType: 20801us [20801us] (47.74%; 91.96%)
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 f3e20fabe4..b441f306e4 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 39.953472 ms
+ Convolution: 34.765216 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 28c4bf36ef..f8f20a02cb 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
@@ -602,7 +602,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.364519 ms
+ conv2d with tensor core: 12.789965 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 753ddc9f97..c325d0ef7c 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018115
- Baseline: 3.214453
+ Numpy running time: 0.019491
+ Baseline: 3.326171
@@ -224,7 +224,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.296729
+ Opt1: 0.326349
@@ -312,7 +312,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.328841
+ Opt2: 0.346240
@@ -397,7 +397,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114458
+ Opt3: 0.130476
@@ -511,7 +511,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109586
+ Opt4: 0.110579
@@ -620,7 +620,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111330
+ Opt5: 0.112296
@@ -730,7 +730,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147028
+ Opt6: 0.148557
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 6959bc6e9b..9cfb0e6540 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
=================
-**00:34.282** total execution time for **how_to_optimize_operators** files:
+**00:35.717** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.536 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.912 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.633 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.150 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.172 | 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 4dd1719355..64dd8f7cca 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
=================
-**09:20.255** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:49.224** 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``) | 05:36.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:01.402 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:39.221 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:42.322 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:05.990 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:08.143 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.691 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.685 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.177 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:15.017 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.059 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.655 | 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 c572561596..95a64df8c1 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
@@ -241,481 +241,760 @@ cooperative fetching, unrolling and operator fusion.
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 28)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([72], "float32", "shared")
- kernel_shared = T.allocate([3072], "float32", "shared")
+ T.launch_thread(blockIdx_x, 128)
+ conv2d_nchw = T.allocate([2], "float32", "local")
+ pad_temp_shared = T.allocate([2016], "float32", "shared")
+ kernel_shared = T.allocate([384], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 64)
- conv2d_nchw_1 = T.buffer_decl((14,), data=conv2d_nchw, scope="local", align=32)
+ T.launch_thread(threadIdx_x, 98)
+ conv2d_nchw_1 = T.buffer_decl((2,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(64, 3):
- cse_var_2: T.int32 = rc_outer_outer * 72
- cse_var_1: T.int32 = ry_outer_outer * 3
+ for rc_outer_outer in range(16):
+ cse_var_2: T.int32 = rc_outer_outer * 1568
+ cse_var_1: T.int32 = rc_outer_outer * 288
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.buffer_decl((72,), data=pad_temp_shared, scope="shared")
- with T.launch_thread(threadIdx_x_1, 64):
- data_1 = T.buffer_decl((25088,), data=data.data)
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 * 4 % 9 and threadIdx_x_1 * 4 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 * 4 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 * 4 % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 1) % 9 and (threadIdx_x_1 * 4 + 1) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 1) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 1) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 2] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 2) % 9 and (threadIdx_x_1 * 4 + 2) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 2) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 2) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 3] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 3) % 9 and (threadIdx_x_1 * 4 + 3) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 3) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1 = T.buffer_decl((2016,), data=pad_temp_shared, scope="shared")
+ data_1 = T.buffer_decl((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 63 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(9 <= (threadIdx_x_1 + 35) % 63 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(9 <= (threadIdx_x_1 + 7) % 63 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(9 <= (threadIdx_x_1 + 42) % 63 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(9 <= (threadIdx_x_1 + 14) % 63 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(9 <= (threadIdx_x_1 + 49) % 63 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(9 <= (threadIdx_x_1 + 21) % 63 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(9 <= (threadIdx_x_1 + 56) % 63 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(9 <= (threadIdx_x_1 + 28) % 63 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(9 <= threadIdx_x_1 % 63 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 678], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(9 <= (threadIdx_x_1 + 35) % 63 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(9 <= (threadIdx_x_1 + 7) % 63 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(9 <= (threadIdx_x_1 + 42) % 63 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(9 <= (threadIdx_x_1 + 14) % 63 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else(9 <= (threadIdx_x_1 + 49) % 63 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else(9 <= (threadIdx_x_1 + 21) % 63 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(9 <= (threadIdx_x_1 + 56) % 63 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else(9 <= (threadIdx_x_1 + 28) % 63 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(9 <= threadIdx_x_1 % 63 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 1364], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else(9 <= (threadIdx_x_1 + 35) % 63 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ if T.likely(threadIdx_x_1 < 56):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else(9 <= (threadIdx_x_1 + 7) % 63 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.buffer_decl((3072,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.buffer_decl((384,), data=kernel_shared, scope="shared")
kernel_1 = T.buffer_decl((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 64] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 128] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 192] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 256] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 320] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 384] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 512] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 576] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 640] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 704] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 768] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 832] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 960] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1024] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1088] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1152] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1216] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1280] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1408] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1472] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1536] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 294912]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1600] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1664] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1728] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 331776]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1792] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1856] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1920] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 368640]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1984] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2048] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2112] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 405504]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2176] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2240] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2304] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 442368]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2368] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2432] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2496] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 479232]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2560] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2624] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 516096]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2752] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2816] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2880] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 552960]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2944] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 3008] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 47]
- for i1_inner, i3_inner in T.grid(2, 7):
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 96 * 4608 + cse_var_1 + threadIdx_x_2 % 96 // 3 * 9 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 98) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 96 // 3 * 9 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 196) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 96 // 3 * 9 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ if T.likely(threadIdx_x_2 < 90):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 294) // 96 * 4608 + cse_var_1 + threadIdx_x_2 // 3 * 9 + threadIdx_x_2 % 3 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 102]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 105]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 108]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 111]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 114]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 117]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 120]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 27]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 123]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 30]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 126]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 33]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 129]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 132]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 39]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 135]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 42]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 138]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 97]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 103]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 106]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 109]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 112]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 115]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 118]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 25]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 121]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 28]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 124]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 31]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 127]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 34]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 130]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 37]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 133]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 40]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 136]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 43]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 139]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 98]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 101]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 104]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 107]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 110]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 113]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 116]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 119]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 26]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 122]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 29]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 125]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 32]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 128]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 35]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 131]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 38]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 134]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 41]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 137]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 44]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 140]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 143]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 144]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 147]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 150]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 153]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 156]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 159]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 168]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 171]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 174]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 177]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 180]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 183]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 186]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 93]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 189]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 145]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 148]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 151]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 154]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 157]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 169]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 172]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 175]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 178]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 181]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 184]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 187]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 94]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 190]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 146]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 149]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 152]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 155]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 158]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 170]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 173]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 176]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 179]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 182]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 185]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 188]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 95]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 191]
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 685], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else(1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 1371], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ if T.likely(threadIdx_x_1 < 56):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else(1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 96 * 4608 + cse_var_1 + threadIdx_x_2 % 96 // 3 * 9 + threadIdx_x_2 % 3 + 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 98) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 96 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 196) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 96 // 3 * 9 + (threadIdx_x_2 + 1) % 3 + 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ if T.likely(threadIdx_x_2 < 90):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 294) // 96 * 4608 + cse_var_1 + threadIdx_x_2 // 3 * 9 + threadIdx_x_2 % 3 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 102]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 105]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 108]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 111]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 114]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 117]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 120]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 27]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 123]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 30]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 126]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 33]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 129]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 132]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 39]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 135]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 42]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 138]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 97]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 103]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 106]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 109]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 112]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 115]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 118]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 25]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 121]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 28]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 124]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 31]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 127]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 34]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 130]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 37]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 133]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 40]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 136]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 43]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 139]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 98]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 101]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 104]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 107]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 110]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 113]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 116]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 119]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 26]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 122]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 29]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 125]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 32]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 128]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 35]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 131]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 38]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 134]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 41]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 137]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 44]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 140]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 143]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 144]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 147]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 150]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 153]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 156]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 159]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 168]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 171]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 174]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 177]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 180]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 183]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 186]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 93]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 189]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 145]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 148]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 151]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 154]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 157]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 169]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 172]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 175]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 178]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 181]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 184]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 187]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 94]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 190]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 146]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 149]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 152]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 155]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 158]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 170]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 173]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 176]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 179]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 182]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 185]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 188]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 95]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 191]
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(threadIdx_x_1 % 63 < 54 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else((threadIdx_x_1 + 35) % 63 < 54 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else((threadIdx_x_1 + 7) % 63 < 54 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else((threadIdx_x_1 + 42) % 63 < 54 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 9 * 7 + (threadIdx_x_1 + 6) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else((threadIdx_x_1 + 14) % 63 < 54 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 9 * 7 + (threadIdx_x_1 + 5) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else((threadIdx_x_1 + 49) % 63 < 54 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 9 * 7 + (threadIdx_x_1 + 4) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else((threadIdx_x_1 + 21) % 63 < 54 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 9 * 7 + (threadIdx_x_1 + 3) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else((threadIdx_x_1 + 56) % 63 < 54 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 9 * 7 + (threadIdx_x_1 + 2) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else((threadIdx_x_1 + 28) % 63 < 54 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 9 * 7 + (threadIdx_x_1 + 1) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(threadIdx_x_1 % 63 < 54 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 692], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else((threadIdx_x_1 + 35) % 63 < 54 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else((threadIdx_x_1 + 7) % 63 < 54 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else((threadIdx_x_1 + 42) % 63 < 54 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 9 * 7 + (threadIdx_x_1 + 6) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else((threadIdx_x_1 + 14) % 63 < 54 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 9 * 7 + (threadIdx_x_1 + 5) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else((threadIdx_x_1 + 49) % 63 < 54 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 9 * 7 + (threadIdx_x_1 + 4) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else((threadIdx_x_1 + 21) % 63 < 54 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 9 * 7 + (threadIdx_x_1 + 3) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else((threadIdx_x_1 + 56) % 63 < 54 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 9 * 7 + (threadIdx_x_1 + 2) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else((threadIdx_x_1 + 28) % 63 < 54 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 9 * 7 + (threadIdx_x_1 + 1) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(threadIdx_x_1 % 63 < 54 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 1378], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else((threadIdx_x_1 + 35) % 63 < 54 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ if T.likely(threadIdx_x_1 < 56):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else((threadIdx_x_1 + 7) % 63 < 54 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 96 * 4608 + cse_var_1 + threadIdx_x_2 % 96 // 3 * 9 + threadIdx_x_2 % 3 + 6]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 98) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 96 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 6]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 196) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 96 // 3 * 9 + (threadIdx_x_2 + 1) % 3 + 6]
+ with T.launch_thread(threadIdx_x_2, 98):
+ if T.likely(threadIdx_x_2 < 90):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 294) // 96 * 4608 + cse_var_1 + threadIdx_x_2 // 3 * 9 + threadIdx_x_2 % 3 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 102]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 105]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 108]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 111]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 114]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 117]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 120]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 27]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 123]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 30]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 126]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 33]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 129]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 132]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 39]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 135]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 42]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 138]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 97]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 103]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 106]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 109]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 112]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 115]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 118]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 25]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 121]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 28]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 124]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 31]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 127]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 34]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 130]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 37]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 133]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 40]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 136]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 43]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 139]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 98]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 101]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 104]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 107]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 110]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 113]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 116]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 119]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 26]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 122]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 29]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 125]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 32]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 128]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 35]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 131]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 38]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 134]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 41]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 137]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 44]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 140]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 143]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 144]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 147]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 150]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 153]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 156]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 159]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 168]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 171]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 174]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 177]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 180]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 183]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 186]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 93]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 189]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 145]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 148]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 151]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 154]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 157]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 169]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 172]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 175]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 178]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 181]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 184]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 187]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 94]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 190]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 146]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 149]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 152]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 155]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 158]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 170]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 173]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 176]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 179]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 182]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 185]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 188]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 95]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 191]
+ for i1_inner in range(2):
compute_1 = T.buffer_decl((25088,), data=compute.data)
bias_1 = T.buffer_decl((512,), data=bias.data)
- compute_1[blockIdx_x // 7 * 6272 + threadIdx_x * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 196 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 4 + threadIdx_x // 49 * 2 + i1_inner], T.float32(0))
@@ -765,7 +1044,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.357 ms
+ Execution time of this operator: 0.353 ms
@@ -813,20 +1092,20 @@ 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=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
@@ -836,13 +1115,13 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, 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)
@@ -862,14 +1141,14 @@ 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=64)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=4)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -887,430 +1166,685 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[384];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((9 <= ((((int)threadIdx.x) + 7) % 63)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((9 <= ((((int)threadIdx.x) + 42) % 63)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((9 <= ((((int)threadIdx.x) + 14) % 63)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((9 <= ((((int)threadIdx.x) + 49) % 63)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((9 <= ((((int)threadIdx.x) + 21) % 63)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = ((((9 <= ((((int)threadIdx.x) + 56) % 63)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((9 <= ((((int)threadIdx.x) + 28) % 63)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((9 <= ((((int)threadIdx.x) + 7) % 63)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((9 <= ((((int)threadIdx.x) + 42) % 63)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((9 <= ((((int)threadIdx.x) + 14) % 63)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((9 <= ((((int)threadIdx.x) + 49) % 63)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = ((((9 <= ((((int)threadIdx.x) + 21) % 63)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((9 <= ((((int)threadIdx.x) + 56) % 63)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = ((((9 <= ((((int)threadIdx.x) + 28) % 63)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = ((((2 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 90) {
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 18)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 685)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 1371)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 1) % 3)) + 3)];
+ if (((int)threadIdx.x) < 90) {
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 21)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((((int)threadIdx.x) + 7) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((((((int)threadIdx.x) + 42) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((((int)threadIdx.x) + 14) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((((((int)threadIdx.x) + 49) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((((int)threadIdx.x) + 21) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = ((((((((int)threadIdx.x) + 56) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((((((int)threadIdx.x) + 28) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 692)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((((int)threadIdx.x) + 7) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((((((int)threadIdx.x) + 42) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((((int)threadIdx.x) + 14) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((((((int)threadIdx.x) + 49) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = ((((((((int)threadIdx.x) + 21) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((((((int)threadIdx.x) + 56) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = ((((((((int)threadIdx.x) + 28) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 1378)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 1) % 3)) + 6)];
+ if (((int)threadIdx.x) < 90) {
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 24)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 4) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1372,7 +1906,7 @@ 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 36.116 seconds)
+ **Total running time of the script:** ( 6 minutes 1.402 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 898be227ff..8872bc2f20 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9267 7.9273 7.9405 7.9122 0.0115
+ 7.8978 7.8994 7.9028 7.8912 0.0049
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.990 seconds)
+ **Total running time of the script:** ( 1 minutes 8.143 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 afe85429e5..05db095d18 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 758.1683 758.4689 759.1544 756.8816 0.9519
+ 756.8337 756.6105 758.7611 755.1294 1.4910
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 39.221 seconds)
+ **Total running time of the script:** ( 1 minutes 42.322 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 61693cf824..94b69e3204 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
@@ -386,74 +386,26 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.buffer_decl((1024,), data=compute_1)
- for nb_j_inner in range(2):
- for i_inner_init in range(32):
- cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
- compute_2[cse_var_1] = T.float32(0)
- compute_2[cse_var_1 + 1] = T.float32(0)
- compute_2[cse_var_1 + 2] = T.float32(0)
- compute_2[cse_var_1 + 3] = T.float32(0)
- compute_2[cse_var_1 + 4] = T.float32(0)
- compute_2[cse_var_1 + 5] = T.float32(0)
- compute_2[cse_var_1 + 6] = T.float32(0)
- compute_2[cse_var_1 + 7] = T.float32(0)
- compute_2[cse_var_1 + 8] = T.float32(0)
- compute_2[cse_var_1 + 9] = T.float32(0)
- compute_2[cse_var_1 + 10] = T.float32(0)
- compute_2[cse_var_1 + 11] = T.float32(0)
- compute_2[cse_var_1 + 12] = T.float32(0)
- compute_2[cse_var_1 + 13] = T.float32(0)
- compute_2[cse_var_1 + 14] = T.float32(0)
- compute_2[cse_var_1 + 15] = T.float32(0)
- for elem_idx, i_inner in T.grid(T.let(cse_var_2, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 32):
- cse_var_2 = T.var("int32")
+ for i0_outer_i1_outer_fused in T.parallel(16):
+ compute_1 = T.allocate([4096], "float32", "global")
+ compute_2 = T.buffer_decl((4096,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(32, 2):
+ for i_inner_init, j_init in T.grid(4, 16):
+ compute_2[i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused * 2 + nb_j_inner, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 4, 16):
+ cse_var_1 = T.var("int32")
placeholder_5 = T.buffer_decl((33,), "int32", data=placeholder_3.data)
- cse_var_21: T.int32 = elem_idx * 16
- cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
- cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i_inner * 256
- cse_var_17: T.int32 = cse_var_20 + 9
- cse_var_16: T.int32 = cse_var_20 + 8
- cse_var_15: T.int32 = cse_var_20 + 7
- cse_var_14: T.int32 = cse_var_20 + 6
- cse_var_13: T.int32 = cse_var_20 + 5
- cse_var_12: T.int32 = cse_var_20 + 4
- cse_var_11: T.int32 = cse_var_20 + 3
- cse_var_10: T.int32 = cse_var_20 + 2
- cse_var_9: T.int32 = cse_var_20 + 15
- cse_var_8: T.int32 = cse_var_20 + 14
- cse_var_7: T.int32 = cse_var_20 + 13
- cse_var_6: T.int32 = cse_var_20 + 12
- cse_var_5: T.int32 = cse_var_20 + 11
- cse_var_4: T.int32 = cse_var_20 + 10
- cse_var_3: T.int32 = cse_var_20 + 1
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.buffer_decl((78656,), data=placeholder_1.data)
placeholder_7 = T.buffer_decl((32768,), data=placeholder.data)
placeholder_8 = T.buffer_decl((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- for i0_inner, i1_inner in T.grid(32, 32):
- cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i_outer_inner * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(128, 32):
+ cse_var_4: T.int32 = i0_inner * 512 + i0_outer_i1_outer_fused * 32 + i1_inner
compute_3 = T.buffer_decl((65536,), data=compute.data)
placeholder_5 = T.buffer_decl((65536,), data=placeholder_4.data)
- compute_3[cse_var_22] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_22], T.float32(0))
+ compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
@@ -503,7 +455,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.754 ms
+ Execution time of this operator: 1.475 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 0d86542ffc..9b523669f9 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
=================
-**00:26.869** total execution time for **how_to_tune_with_autotvm** files:
+**00:30.121** 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``) | 00:26.835 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:30.087 | 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 4c1b96cfd1..8421cc762f 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -390,8 +390,9 @@ 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, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2214411
- 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, 8, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8688131
+ No: 2 GFLOPS: 3.47/3.47 result: MeasureResult(costs=(0.06669478599999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.769287347793579, timestamp=1674607135.604493) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6206840
+ No: 3 GFLOPS: 0.00/3.47 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
@@ -513,8 +514,8 @@ 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, 16, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2836600
- 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, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,87647
+ No: 4 GFLOPS: 0.00/3.47 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
@@ -636,8 +637,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3432632
- 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, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9995123
+ No: 5 GFLOPS: 0.00/3.47 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
@@ -759,8 +760,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1447163
- 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, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8624261
+ No: 6 GFLOPS: 0.00/3.47 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
@@ -882,8 +883,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6784467
- 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, 32, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4967045
+ No: 7 GFLOPS: 0.00/3.47 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
@@ -1005,8 +1006,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1826993
- No: 7 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, 4, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2252786
+ No: 8 GFLOPS: 72.15/72.15 result: MeasureResult(costs=(0.0032085432790697676,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.026492118835449, timestamp=1674607139.8619287) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4138423
+ No: 9 GFLOPS: 192.90/192.90 result: MeasureResult(costs=(0.0012000854056603773,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.224464178085327, timestamp=1674607142.2581093) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4666258
+ No: 10 GFLOPS: 0.00/192.90 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
@@ -1128,8 +1131,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4946347
- No: 8 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, 1, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,946830
+ No: 11 GFLOPS: 7.34/192.90 result: MeasureResult(costs=(0.0315600965,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3601210117340088, timestamp=1674607143.089132) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5634830
+ No: 12 GFLOPS: 0.00/192.90 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
@@ -1251,8 +1255,8 @@ 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, 1, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5782830
- No: 9 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, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,642790
+ No: 13 GFLOPS: 0.00/192.90 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
@@ -1374,8 +1378,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4312082
- No: 10 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, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1470120
+ No: 14 GFLOPS: 0.00/192.90 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
@@ -1497,8 +1501,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4059898
- No: 11 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, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,906292
+ No: 15 GFLOPS: 0.00/192.90 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
@@ -1620,8 +1624,9 @@ 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, 16, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8588314
- No: 12 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, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5110594
+ No: 16 GFLOPS: 5.50/192.90 result: MeasureResult(costs=(0.042091648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.724987268447876, timestamp=1674607146.0543864) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8018703
+ No: 17 GFLOPS: 0.00/192.90 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
@@ -1743,8 +1748,8 @@ 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, 1, 16, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4180378
- No: 13 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, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2504378
+ No: 18 GFLOPS: 0.00/192.90 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
@@ -1866,9 +1871,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1613938
- No: 14 GFLOPS: 67.22/67.22 result: MeasureResult(costs=(0.0034440511,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.426131010055542, timestamp=1674597919.1928568) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5338876
- No: 15 GFLOPS: 0.00/67.22 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,753752
+ No: 19 GFLOPS: 0.00/192.90 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
@@ -1990,8 +1994,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4238664
- No: 16 GFLOPS: 0.00/67.22 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, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1130988
+ No: 20 GFLOPS: 0.00/192.90 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
@@ -2113,255 +2117,7 @@ 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, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6831409
- No: 17 GFLOPS: 6.32/67.22 result: MeasureResult(costs=(0.036649433,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.555211544036865, timestamp=1674597923.9573052) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8132850
- No: 18 GFLOPS: 8.31/67.22 result: MeasureResult(costs=(0.027861503500000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5806710720062256, timestamp=1674597924.7226763) [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5490176
- No: 19 GFLOPS: 0.00/67.22 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3785226
- No: 20 GFLOPS: 0.00/67.22 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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, 16, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3839999
+ 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, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2357860
@@ -2416,9 +2172,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5338876
+ [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4666258
Finish loading 20 records
- Time cost of this operator: 0.003815
+ Time cost of this operator: 0.001368
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 2ce48c6033..73a6485087 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
@@ -363,10 +363,10 @@ 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 312.5 98.728 (1, 2, 10, 10, 3) 2 1 [312.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.961 (1, 6, 10, 10) 1 1 [3.042]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.985 0.311 (1, 1, 10, 10, 3) 1 1 [0.985]
- Total_time - 316.528 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.727 (1, 2, 10, 10, 3) 2 1 [309.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.028 0.965 (1, 6, 10, 10) 1 1 [3.028]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.307 (1, 1, 10, 10, 3) 1 1 [0.963]
+ Total_time - 313.591 - - - - -
@@ -431,10 +431,10 @@ 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 102.9 97.492 (1, 6, 10, 10, 1) 2 1 [102.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.783 1.69 (1, 6, 10, 10) 1 1 [1.783]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.864 0.819 (1, 3, 10, 10, 1) 1 1 [0.864]
- Total_time - 105.548 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.2 97.421 (1, 6, 10, 10, 1) 2 1 [103.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.761 1.662 (1, 6, 10, 10) 1 1 [1.761]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.917 (1, 1, 10, 10, 3) 1 1 [0.972]
+ Total_time - 105.932 - - - - -
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 25644540f2..9c2a3181e9 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
@@ -117,7 +117,7 @@ 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, 36.5MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 18.1MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 28.3MB/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.
@@ -322,7 +322,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.962 seconds)
+ **Total running time of the script:** ( 1 minutes 13.935 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 fe3240c809..6ab5f0e797 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp5gq4omcf/images/random'
+ '/tmp/tmpv5rhl63h/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp5gq4omcf/images/target contains 8144 images
- /tmp/tmp5gq4omcf/images/random contains 5000 images
+ /tmp/tmpv5rhl63h/images/target contains 8144 images
+ /tmp/tmpv5rhl63h/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2153 - accuracy: 0.9278 - val_loss: 0.1581 - val_accuracy: 0.9464 - 47s/epoch - 142ms/step
+ 328/328 - 48s - loss: 0.2294 - accuracy: 0.9217 - val_loss: 0.1326 - val_accuracy: 0.9535 - 48s/epoch - 146ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0879 - accuracy: 0.9652 - val_loss: 0.2606 - val_accuracy: 0.9120 - 43s/epoch - 131ms/step
+ 328/328 - 44s - loss: 0.0975 - accuracy: 0.9639 - val_loss: 0.0903 - val_accuracy: 0.9641 - 44s/epoch - 134ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0638 - accuracy: 0.9756 - val_loss: 0.1235 - val_accuracy: 0.9596 - 43s/epoch - 131ms/step
+ 328/328 - 44s - loss: 0.0681 - accuracy: 0.9748 - val_loss: 0.1928 - val_accuracy: 0.9377 - 44s/epoch - 134ms/step
- <keras.callbacks.History object at 0x7f7af7237e50>
+ <keras.callbacks.History object at 0x7f12803d7750>
@@ -857,7 +857,7 @@ 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 43.647 seconds)
+ **Total running time of the script:** ( 5 minutes 58.815 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 8ac05ddc00..c445d512a4 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
@@ -5,23 +5,23 @@
Computation times
=================
-**06:57.822** total execution time for **how_to_work_with_microtvm** files:
+**08:20.689** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:43.647 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:58.815 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:09.962 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:13.935 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.346 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:54.606 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.289 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.862 | 0.0 MB |
-+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.043 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
++---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_mlperftiny.py` (``micro_mlperftiny.py``) | 00:00.000 | 0.0 MB |
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 050323c00e..165033109d 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
=================
-**00:44.398** total execution time for **how_to_work_with_relay** files:
+**00:46.332** 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``) | 00:32.660 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:34.197 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.221 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.465 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.511 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.665 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 3426fedbbb..de894c916c 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f7bb32e08c0>
+ <function my_cuda_math_rule at 0x7f128002c8c0>
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 aee10b62cc..f785c2d6ad 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
=================
-**00:07.714** total execution time for **how_to_work_with_schedules** files:
+**00:08.240** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.203 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.681 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.154 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.142 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.578 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.602 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.559 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.580 | 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_extern_op.py` (``extern_op.py``) | 00:00.121 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.054 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.033 | 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``) | 00:00.026 | 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 10312440aa..d8606f27cf 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -328,7 +328,7 @@ The importing needs to happen before the tensorized GEMV being executed.
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmptdv9y8gy/input0.cc'\nsource_filename = \"/tmp/tmptdv9y8gy/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca float*, [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmp3l6i0t5_/input0.cc'\nsource_filename = \"/tmp/tmp3l6i0t5_/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca float*, [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 6e398e5534..5b31e2c382 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
=================
-**00:30.126** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:31.678** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:30.119 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.671 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 37fd5d4b21..d86cc2dceb 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 31.84s!
+ resnet18_v1 inference graph built in 34.21s!
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 179045e2b7..7865d64218 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 21.70s!
+ yolov3-tiny inference graph built in 23.11s!
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 01d2479493..9e156236c4 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
=================
-**01:37.523** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.850** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.897 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.963 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.626 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.886 | 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 07104f1ec4..eb78d4e22f 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
=================
-**00:03.151** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.185** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.690 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.701 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.461 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.484 | 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 1badd479b9..c52624f9c6 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
=================
-**00:00.829** total execution time for **topic_vta_tutorials** files:
+**00:00.848** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.447 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.452 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.382 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.396 | 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 b969a857a2..605ff0a58b 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -315,7 +315,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.948 ms
+ Execution time of this operator: 97.652 ms
@@ -433,7 +433,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 30.778 seconds)
+ **Total running time of the script:** ( 1 minutes 18.472 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 3a6e103dbc..be4a272d96 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 4.03/4.03 result: MeasureResult(costs=(0.0665344914,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3244342803955078, timestamp=1674596386.7180634) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
- No: 2 GFLOPS: 1.52/4.03 result: MeasureResult(costs=(0.1761633742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0483696460723877, timestamp=1674596389.7901013) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 3 GFLOPS: 3.58/4.03 result: MeasureResult(costs=(0.074977614,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4274747371673584, timestamp=1674596392.0094767) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
- No: 4 GFLOPS: 9.84/9.84 result: MeasureResult(costs=(0.027278134,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6544194221496582, timestamp=1674596393.4573526) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
- No: 5 GFLOPS: 2.05/9.84 result: MeasureResult(costs=(0.1310160126,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.335326910018921, timestamp=1674596395.9506965) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
- No: 6 GFLOPS: 1.53/9.84 result: MeasureResult(costs=(0.1753398468,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0451152324676514, timestamp=1674596399.0077999) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
- No: 7 GFLOPS: 12.83/12.83 result: MeasureResult(costs=(0.0209167524,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5756168365478516, timestamp=1674596400.361693) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
- No: 8 GFLOPS: 10.22/12.83 result: MeasureResult(costs=(0.026265427199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7072844505310059, timestamp=1674596401.0454895) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
- No: 9 GFLOPS: 0.49/12.83 result: MeasureResult(costs=(0.5476163484,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.956401586532593, timestamp=1674596410.4374497) [('tile_y', [-1, 512]), ('tile_x', [-1, 1])],None,9
- No: 10 GFLOPS: 9.97/12.83 result: MeasureResult(costs=(0.026912496599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9544336795806885, timestamp=1674596411.1279078) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
+ No: 1 GFLOPS: 13.72/13.72 result: MeasureResult(costs=(0.019565723,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6486637592315674, timestamp=1674605543.5546534) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+ No: 2 GFLOPS: 2.09/13.72 result: MeasureResult(costs=(0.1282078978,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2927780151367188, timestamp=1674605545.8597195) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
+ No: 3 GFLOPS: 10.14/13.72 result: MeasureResult(costs=(0.026475696,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.695953369140625, timestamp=1674605547.344637) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 4 GFLOPS: 14.46/14.46 result: MeasureResult(costs=(0.018567763199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5841853618621826, timestamp=1674605548.6924732) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+ No: 5 GFLOPS: 1.93/14.46 result: MeasureResult(costs=(0.1390463474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4539122581481934, timestamp=1674605552.1041887) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 6 GFLOPS: 0.91/14.46 result: MeasureResult(costs=(0.2955401568,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.967718601226807, timestamp=1674605557.0880978) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
+ No: 7 GFLOPS: 2.68/14.46 result: MeasureResult(costs=(0.10025012200000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8336126804351807, timestamp=1674605558.9435222) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
+ No: 8 GFLOPS: 9.82/14.46 result: MeasureResult(costs=(0.027340350799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7244877815246582, timestamp=1674605559.6449897) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
+ No: 9 GFLOPS: 3.07/14.46 result: MeasureResult(costs=(0.0874497842,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6150307655334473, timestamp=1674605561.4790967) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
+ No: 10 GFLOPS: 10.71/14.46 result: MeasureResult(costs=(0.025064742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7141749858856201, timestamp=1674605562.1377146) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 26da424cfa..f91787fda9 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 512.7073828600169, 'median': 513.0480596500092, 'std': 2.1568353339191852}
+ {'mean': 522.5552605600002, 'median': 522.2551564499952, 'std': 2.2707577388213855}
@@ -545,30 +545,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.68/ 19.22 GFLOPS | Progress: (4/20) | 8.47 s
[Task 1/25] Current/Best: 12.94/ 19.22 GFLOPS | Progress: (8/20) | 12.10 s
[Task 1/25] Current/Best: 16.05/ 19.22 GFLOPS | Progress: (12/20) | 14.89 s
[Task 1/25] Current/Best: 11.29/ 22.81 GFLOPS | Progress: (16/20) | 17.40 s
[Task 1/25] Current/Best: 23.32/ 23.32 GFLOPS | Progress: (20/20) | 19.45 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 9.27/ 15.06 GFLOPS | Progress: (4/20) | 4.69 s
[Task 2/25] Current/Best: 17.43/ 17.43 GFLOPS | Progress: (8/20) | 6.81 s
[Task 2/25] Current/Best: 10.97/ 21.25 GFLOPS | Progress: (12/20) | 8.32 s
[Task 2/25] Current/Best: 13.94/ 21.25 GFLOPS | Progress: (16/20) | 11.07 s
[Task 2/25] Current/Best: 13.52/ 21.25 GFLOPS | Progress: (20/20) | 12.72 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 16.64/ 16.64 GFLOPS | Progress: (4/20) | 4.18 s
[Task 3/25] Current/Best: 9.80/ 16.64 GFLOPS | Progress: (8/20) | 6.51 s
[Task 3/25] Current/Best: 14.18/ 23.24 GFLOPS | Progress: (12/20) | 8.62 s
[Task 3/25] Current/Best: 3.14/ 23.24 GFLOPS | Progress: (16/20) | 11.42 s
[Task 3/25] Current/Best: 20.35/ 23.24 GFLOPS | Progress: (20/20) | 14.67 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.67/ 11.33 GFLOPS | Progress: (4/20) | 5.10 s
[Task 4/25] Current/Best: 9.46/ 16.21 GFLOPS | Progress: (8/20) | 8.20 s
[Task 4/25] Current/Best: 12.40/ 16.21 GFLOPS | Progress: (12/20) | 11.07 s
[Task 4/25] Current/Best: 5.89/ 16.21 GFLOPS | Progress: (16/20) | 13.05 s
[Task 4/25] Current/Best: 22.75/ 22.75 GFLOPS | Progress: (20/20) | 14.54 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.08/ 18.57 GFLOPS | Progress: (4/20) | 4.24 s
[Task 5/25] Current/Best: 12.16/ 18.57 GFLOPS | Progress: (8/20) | 7.80 s
[Task 5/25] Current/Best: 4.39/ 18.57 GFLOPS | Progress: (12/20) | 10.03 s
[Task 5/25] Current/Best: 3.39/ 18.57 GFLOPS | Progress: (16/20) | 12.65 s
[Task 5/25] Current/Best: 14.61/ 19.22 GFLOPS | Progress: (20/20) | 14.98 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 13.81/ 13.95 GFLOPS | Progress: (4/20) | 4.50 s
[Task 6/25] Current/Best: 3.08/ 14.53 GFLOPS | Progress: (8/20) | 7.89 s
[Task 6/25] Current/Best: 11.73/ 16.16 GFLOPS | Progress: (12/20) | 11.80 s
[Task 6/25] Current/Best: 11.68/ 16.98 GFLOPS | Progress: (16/20) | 14.42 s
[Task 6/25] Current/Best: 22.77/ 22.77 GFLOPS | Progress: (20/20) | 16.80 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.38/ 18.55 GFLOPS | Progress: (4/20) | 4.18 s
[Task 7/25] Current/Best: 13.03/ 22.72 GFLOPS | Progress: (8/20) | 6.22 s
[Task 7/25] Current/Best: 13.04/ 22.72 GFLOPS | Progress: (12/20) | 8.44 s
[Task 7/25] Current/Best: 5.60/ 22.72 GFLOPS | Progress: (16/20) | 11.28 s
[Task 7/25] Current/Best: 12.54/ 22.72 GFLOPS | Progress: (20/20) | 13.79 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 1.69/ 13.95 GFLOPS | Progress: (4/20) | 8.49 s
[Task 8/25] Current/Best: 4.80/ 13.95 GFLOPS | Progress: (8/20) | 15.53 s
[Task 8/25] Current/Best: 8.43/ 13.95 GFLOPS | Progress: (12/20) | 26.54 s
[Task 8/25] Current/Best: 6.87/ 14.08 GFLOPS | Progress: (16/20) | 29.57 s
[Task 8/25] Current/Best: 16.26/ 16.26 GFLOPS | Progress: (20/20) | 32.17 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.23/ 23.12 GFLOPS | Progress: (4/20) | 4.80 s
[Task 9/25] Current/Best: 21.19/ 23.12 GFLOPS | Progress: (8/20) | 6.48 s
[Task 9/25] Current/Best: 16.24/ 23.12 GFLOPS | Progress: (12/20) | 8.04 s
[Task 9/25] Current/Best: 5.15/ 23.12 GFLOPS | Progress: (16/20) | 15.03 s
[Task 9/25] Current/Best: 15.45/ 23.12 GFLOPS | Progress: (20/20) | 17.94 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 1.59/ 9.98 GFLOPS | Progress: (4/20) | 5.58 s
[Task 10/25] Current/Best: 13.95/ 17.85 GFLOPS | Progress: (8/20) | 7.58 s
[Task 10/25] Current/Best: 16.08/ 17.85 GFLOPS | Progress: (12/20) | 9.78 s
[Task 10/25] Current/Best: 13.64/ 18.91 GFLOPS | Progress: (16/20) | 11.75 s
[Task 10/25] Current/Best: 15.96/ 18.91 GFLOPS | Progress: (20/20) | 13.66 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 16.02/ 18.88 GFLOPS | Progress: (4/20) | 4.01 s
[Task 11/25] Current/Best: 16.37/ 18.88 GFLOPS | Progress: (8/20) | 6.34 s
[Task 11/25] Current/Best: 8.36/ 18.88 GFLOPS | Progress: (12/20) | 8.84 s
[Task 11/25] Current/Best: 13.10/ 19.55 GFLOPS | Progress: (16/20) | 11.05 s
[Task 11/25] Current/Best: 18.15/ 19.55 GFLOPS | Progress: (20/20) | 13.51 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 3.02/ 18.13 GFLOPS | Progress: (4/20) | 4.26 s
[Task 12/25] Current/Best: 5.46/ 18.13 GFLOPS | Progress: (8/20) | 7.86 s
[Task 12/25] Current/Best: 20.94/ 20.94 GFLOPS | Progress: (12/20) | 9.58 s
[Task 12/25] Current/Best: 4.05/ 20.94 GFLOPS | Progress: (16/20) | 12.72 s
[Task 12/25] Current/Best: 13.57/ 20.94 GFLOPS | Progress: (20/20) | 15.16 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.17/ 23.45 GFLOPS | Progress: (4/20) | 4.96 s
[Task 13/25] Current/Best: 9.76/ 23.45 GFLOPS | Progress: (8/20) | 8.50 s
[Task 13/25] Current/Best: 19.45/ 23.45 GFLOPS | Progress: (12/20) | 12.53 s
[Task 13/25] Current/Best: 18.49/ 23.45 GFLOPS | Progress: (16/20) | 16.01 s
[Task 13/25] Current/Best: 9.66/ 23.45 GFLOPS | Progress: (20/20) | 18.53 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.32/ 22.09 GFLOPS | Progress: (4/20) | 4.60 s
[Task 14/25] Current/Best: 14.13/ 22.09 GFLOPS | Progress: (8/20) | 7.86 s
[Task 14/25] Current/Best: 8.69/ 22.09 GFLOPS | Progress: (12/20) | 10.67 s
[Task 14/25] Current/Best: 2.49/ 22.09 GFLOPS | Progress: (16/20) | 13.53 s
[Task 14/25] Current/Best: 4.44/ 22.09 GFLOPS | Progress: (20/20) | 16.15 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 9.29/ 13.22 GFLOPS | Progress: (4/20) | 6.31 s
[Task 15/25] Current/Best: 16.48/ 16.48 GFLOPS | Progress: (8/20) | 8.69 s
[Task 15/25] Current/Best: 6.16/ 16.48 GFLOPS | Progress: (12/20) | 12.56 s Done.
-
[Task 15/25] Current/Best: 4.88/ 19.73 GFLOPS | Progress: (16/20) | 14.11 s
[Task 15/25] Current/Best: 16.20/ 19.73 GFLOPS | Progress: (20/20) | 18.15 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.69/ 19.69 GFLOPS | Progress: (4/20) | 3.30 s
[Task 16/25] Current/Best: 19.46/ 19.69 GFLOPS | Progress: (8/20) | 5.44 s
[Task 16/25] Current/Best: 12.22/ 19.69 GFLOPS | Progress: (12/20) | 7.81 s
[Task 16/25] Current/Best: 18.55/ 20.67 GFLOPS | Progress: (16/20) | 10.28 s
[Task 16/25] Current/Best: 9.18/ 20.67 GFLOPS | Progress: (20/20) | 11.95 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.17/ 22.42 GFLOPS | Progress: (4/20) | 4.53 s
[Task 17/25] Current/Best: 3.09/ 22.42 GFLOPS | Progress: (8/20) | 7.79 s
[Task 17/25] Current/Best: 22.10/ 22.42 GFLOPS | Progress: (12/20) | 10.96 s
[Task 17/25] Current/Best: 18.08/ 22.42 GFLOPS | Progress: (16/20) | 13.37 s
[Task 17/25] Current/Best: 11.12/ 22.42 GFLOPS | Progress: (20/20) | 15.95 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 5.50/ 17.96 GFLOPS | Progress: (4/20) | 5.52 s
[Task 18/25] Current/Best: 6.56/ 17.96 GFLOPS | Progress: (8/20) | 8.99 s
[Task 18/25] Current/Best: 11.39/ 17.96 GFLOPS | Progress: (12/20) | 11.21 s
[Task 18/25] Current/Best: 13.51/ 19.65 GFLOPS | Progress: (16/20) | 13.57 s
[Task 18/25] Current/Best: 9.10/ 20.72 GFLOPS | Progress: (20/20) | 17.27 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.73/ 15.70 GFLOPS | Progress: (4/20) | 4.80 s
[Task 19/25] Current/Best: 8.96/ 20.53 GFLOPS | Progress: (8/20) | 7.68 s
[Task 19/25] Current/Best: 18.31/ 20.53 GFLOPS | Progress: (12/20) | 11.11 s
[Task 19/25] Current/Best: 20.10/ 20.53 GFLOPS | Progress: (16/20) | 14.14 s
[Task 19/25] Current/Best: 10.57/ 21.95 GFLOPS | Progress: (20/20) | 17.51 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 5.11/ 19.76 GFLOPS | Progress: (4/20) | 3.99 s
[Task 20/25] Current/Best: 14.23/ 19.76 GFLOPS | Progress: (8/20) | 11.09 s
[Task 20/25] Current/Best: 15.33/ 19.76 GFLOPS | Progress: (12/20) | 14.25 s
[Task 20/25] Current/Best: 2.46/ 19.76 GFLOPS | Progress: (16/20) | 17.24 s
[Task 20/25] Current/Best: 9.82/ 19.76 GFLOPS | Progress: (20/20) | 20.29 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.50/ 22.50 GFLOPS | Progress: (4/20) | 3.50 s
[Task 21/25] Current/Best: 13.75/ 22.50 GFLOPS | Progress: (8/20) | 4.82 s
[Task 21/25] Current/Best: 17.35/ 22.50 GFLOPS | Progress: (12/20) | 7.27 s
[Task 21/25] Current/Best: 15.48/ 22.50 GFLOPS | Progress: (16/20) | 8.77 s
[Task 21/25] Current/Best: 10.36/ 22.50 GFLOPS | Progress: (20/20)
| 11.78 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.17/ 20.45 GFLOPS | Progress: (4/20) | 3.47 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 8.59/ 14.34 GFLOPS | Progress: (4/20) | 9.01 s
[Task 1/25] Current/Best: 15.04/ 17.55 GFLOPS | Progress: (8/20) | 13.18 s
[Task 1/25] Current/Best: 12.32/ 17.55 GFLOPS | Progress: (12/20) | 15.78 s
[Task 1/25] Current/Best: 6.33/ 17.55 GFLOPS | Progress: (16/20) | 19.69 s
[Task 1/25] Current/Best: 11.21/ 19.44 GFLOPS | Progress: (20/20) | 22.67 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (4/20) | 3.98 s
[Task 2/25] Current/Best: 11.69/ 20.98 GFLOPS | Progress: (8/20) | 5.76 s
[Task 2/25] Current/Best: 6.18/ 20.98 GFLOPS | Progress: (12/20) | 7.24 s
[Task 2/25] Current/Best: 17.18/ 20.98 GFLOPS | Progress: (16/20) | 8.74 s
[Task 2/25] Current/Best: 14.51/ 20.98 GFLOPS | Progress: (20/20) | 11.17 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 20.05/ 20.05 GFLOPS | Progress: (4/20) | 4.24 s
[Task 3/25] Current/Best: 3.11/ 20.05 GFLOPS | Progress: (8/20) | 7.25 s
[Task 3/25] Current/Best: 6.51/ 20.05 GFLOPS | Progress: (12/20) | 9.59 s
[Task 3/25] Current/Best: 7.26/ 20.05 GFLOPS | Progress: (16/20) | 14.61 s
[Task 3/25] Current/Best: 9.41/ 20.26 GFLOPS | Progress: (20/20) | 17.06 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.79/ 14.33 GFLOPS | Progress: (4/20) | 4.12 s
[Task 4/25] Current/Best: 15.22/ 16.56 GFLOPS | Progress: (8/20) | 5.96 s
[Task 4/25] Current/Best: 15.65/ 18.36 GFLOPS | Progress: (12/20) | 10.88 s
[Task 4/25] Current/Best: 11.82/ 19.34 GFLOPS | Progress: (16/20) | 12.91 s
[Task 4/25] Current/Best: 10.37/ 19.34 GFLOPS | Progress: (20/20) | 17.32 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 13.72/ 15.08 GFLOPS | Progress: (4/20) | 4.12 s
[Task 5/25] Current/Best: 17.69/ 17.69 GFLOPS | Progress: (8/20) | 6.14 s
[Task 5/25] Current/Best: 5.32/ 17.69 GFLOPS | Progress: (12/20) | 8.57 s
[Task 5/25] Current/Best: 10.04/ 17.69 GFLOPS | Progress: (16/20) | 10.68 s
[Task 5/25] Current/Best: 4.00/ 17.69 GFLOPS | Progress: (20/20) | 13.16 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.61/ 17.62 GFLOPS | Progress: (4/20) | 5.32 s
[Task 6/25] Current/Best: 11.21/ 17.62 GFLOPS | Progress: (8/20) | 8.50 s
[Task 6/25] Current/Best: 10.93/ 17.62 GFLOPS | Progress: (12/20) | 11.84 s
[Task 6/25] Current/Best: 12.90/ 17.62 GFLOPS | Progress: (16/20) | 14.32 s
[Task 6/25] Current/Best: 13.38/ 17.62 GFLOPS | Progress: (20/20) | 17.07 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 17.07/ 17.87 GFLOPS | Progress: (4/20) | 4.11 s
[Task 7/25] Current/Best: 8.30/ 17.87 GFLOPS | Progress: (8/20) | 6.90 s
[Task 7/25] Current/Best: 15.18/ 17.87 GFLOPS | Progress: (12/20) | 11.00 s
[Task 7/25] Current/Best: 12.06/ 18.75 GFLOPS | Progress: (16/20) | 14.21 s
[Task 7/25] Current/Best: 4.94/ 18.75 GFLOPS | Progress: (20/20) | 16.68 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.74/ 13.36 GFLOPS | Progress: (4/20) | 6.01 s
[Task 8/25] Current/Best: 10.33/ 13.36 GFLOPS | Progress: (8/20) | 11.74 s
[Task 8/25] Current/Best: 14.73/ 16.55 GFLOPS | Progress: (12/20) | 14.25 s
[Task 8/25] Current/Best: 22.47/ 22.47 GFLOPS | Progress: (16/20) | 17.18 s
[Task 8/25] Current/Best: 14.21/ 22.47 GFLOPS | Progress: (20/20) | 28.60 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (4/20) | 7.51 s
[Task 9/25] Current/Best: 6.61/ 18.71 GFLOPS | Progress: (8/20) | 10.27 s
[Task 9/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (12/20) | 13.21 s
[Task 9/25] Current/Best: 4.76/ 21.22 GFLOPS | Progress: (16/20) | 15.22 s
[Task 9/25] Current/Best: 13.08/ 21.22 GFLOPS | Progress: (20/
20) | 19.84 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 5.96/ 11.04 GFLOPS | Progress: (4/20) | 4.03 s
[Task 10/25] Current/Best: 14.31/ 19.92 GFLOPS | Progress: (8/20) | 6.02 s
[Task 10/25] Current/Best: 16.59/ 19.92 GFLOPS | Progress: (12/20) | 8.04 s
[Task 10/25] Current/Best: 10.28/ 19.92 GFLOPS | Progress: (16/20) | 10.41 s
[Task 10/25] Current/Best: 13.35/ 19.92 GFLOPS | Progress: (20/20) | 12.39 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 8.40/ 16.63 GFLOPS | Progress: (4/20) | 4.50 s
[Task 11/25] Current/Best: 14.80/ 18.51 GFLOPS | Progress: (8/20) | 7.10 s
[Task 11/25] Current/Best: 12.18/ 19.18 GFLOPS | Progress: (12/20) | 9.94 s
[Task 11/25] Current/Best: 6.00/ 19.82 GFLOPS | Progress: (16/20) | 12.22 s
[Task 11/25] Current/Best: 5.52/ 19.82 GFLOPS | Progress: (20/20) | 14.91 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.41/ 17.91 GFLOPS | Progress: (4/20) | 5.09 s
[Task 12/25] Current/Best: 10.65/ 17.91 GFLOPS | Progress: (8/20) | 7.78 s
[Task 12/25] Current/Best: 6.60/ 17.91 GFLOPS | Progress: (12/20) | 11.21 s
[Task 12/25] Current/Best: 3.48/ 17.91 GFLOPS | Progress: (16/20) | 14.69 s
[Task 12/25] Current/Best: 11.47/ 17.91 GFLOPS | Progress: (20/20) | 18.13 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.34/ 18.95 GFLOPS | Progress: (4/20) | 5.18 s
[Task 13/25] Current/Best: 6.55/ 18.95 GFLOPS | Progress: (8/20) | 8.10 s
[Task 13/25] Current/Best: 10.24/ 18.95 GFLOPS | Progress: (12/20) | 11.47 s
[Task 13/25] Current/Best: 11.10/ 21.46 GFLOPS | Progress: (16/20) | 13.89 s
[Task 13/25] Current/Best: 6.08/ 22.33 GFLOPS | Progress: (20/20) | 17.22 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 7.37/ 12.80 GFLOPS | Progress: (4/20) | 5.33 s
[Task 14/25] Current/Best: 4.82/ 12.80 GFLOPS | Progress: (8/20) | 11.32 s
[Task 14/25] Current/Best: 10.89/ 15.01 GFLOPS | Progress: (12/20) | 14.01 s
[Task 14/25] Current/Best: 19.17/ 19.17 GFLOPS | Progress: (16/20) | 16.20 s
[Task 14/25] Current/Best: 12.97/ 19.17 GFLOPS | Progress: (20/20) | 18.65 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 5.71/ 12.34 GFLOPS | Progress: (4/20) | 3.98 s Done.
Done.
-
[Task 22/25] Current/Best: 10.66/ 20.45 GFLOPS | Progress: (8/20) | 5.23 s
[Task 22/25] Current/Best: 19.62/ 20.45 GFLOPS | Progress: (12/20) | 6.88 s
[Task 22/25] Current/Best: 19.07/ 20.45 GFLOPS | Progress: (16/20) | 9.02 s
[Task 22/25] Current/Best: 7.19/ 21.20 GFLOPS | Progress: (20/20) | 11.09 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.80/ 22.50 GFLOPS | Progress: (4/20) | 5.25 s
[Task 23/25] Current/Best: 10.92/ 22.50 GFLOPS | Progress: (8/20) | 9.12 s
[Task 23/25] Current/Best: 7.76/ 22.50 GFLOPS | Progress: (12/20) | 12.63 s
[Task 23/25] Current/Best: 19.11/ 22.50 GFLOPS | Progress: (16/20) | 15.62 s
[Task 23/25] Current/Best: 2.67/ 22.50 GFLOPS | Progress: (20/20) | 19.36 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.24/ 9.07 GFLOPS | Progress: (4/20) | 12.79 s
[Task 24/25] Current/Best: 5.73/ 9.07 GFLOPS | Progress: (8/20) | 23.43 s
[Task 24/25] Current/Best: 3.73/ 9.07 GFLOPS | Progress: (12/20) | 35.37 s
[Task 24/25] Current/Best: 9.71/ 9.71 GFLOPS | Progress: (16/20) | 47.13 s
[Task 24/25] Current/Best: 5.61/ 10.06 GFLOPS | Progress: (20/20) | 50.72 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 1.55/ 8.01 GFLOPS | Progress: (4/20) | 12.75 s
[Task 25/25] Current/Best: 4.24/ 8.01 GFLOPS | Progress: (8/20) | 23.71 s
[Task 25/25] Current/Best: 3.00/ 8.01 GFLOPS | Progress: (12/20) | 35.81 s
[Task 25/25] Current/Best: 1.55/ 8.57 GFLOPS | Progress: (16/20) | 46.46 s
[Task 25/25] Current/Best: 8.26/ 8.57 GFLOPS | Progress: (20/20) | 57.40 s
+
[Task 15/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (8/20) | 8.27 s
[Task 15/25] Current/Best: 4.82/ 18.07 GFLOPS | Progress: (12/20) | 10.48 s
[Task 15/25] Current/Best: 12.54/ 18.07 GFLOPS | Progress: (16/20) | 13.29 s
[Task 15/25] Current/Best: 8.33/ 18.07 GFLOPS | Progress: (20/20) | 19.97 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 13.33/ 18.47 GFLOPS | Progress: (4/20) | 4.53 s
[Task 16/25] Current/Best: 13.21/ 19.90 GFLOPS | Progress: (8/20) | 6.30 s
[Task 16/25] Current/Best: 10.67/ 19.90 GFLOPS | Progress: (12/20) | 8.66 s
[Task 16/25] Current/Best: 18.97/ 19.90 GFLOPS | Progress: (16/20) | 10.32 s
[Task 16/25] Current/Best: 11.12/ 19.90 GFLOPS | Progress: (20/20) | 12.40 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 10.70/ 20.77 GFLOPS | Progress: (4/20) | 4.44 s
[Task 17/25] Current/Best: 12.90/ 20.77 GFLOPS | Progress: (8/20) | 6.64 s
[Task 17/25] Current/Best: 11.32/ 20.77 GFLOPS | Progress: (12/20) | 10.47 s
[Task 17/25] Current/Best: 3.10/ 22.29 GFLOPS | Progress: (16/20) | 13.20 s
[Task 17/25] Current/Best: 12.55/ 22.29 GFLOPS | Progress: (20/20) | 16.61 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 16.89/ 16.89 GFLOPS | Progress: (4/20) | 4.12 s
[Task 18/25] Current/Best: 12.79/ 16.89 GFLOPS | Progress: (8/20) | 7.00 s
[Task 18/25] Current/Best: 15.30/ 19.44 GFLOPS | Progress: (12/20) | 11.31 s
[Task 18/25] Current/Best: 11.55/ 19.44 GFLOPS | Progress: (16/20) | 13.39 s
[Task 18/25] Current/Best: 9.58/ 19.44 GFLOPS | Progress: (20/20) | 15.70 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.34/ 13.16 GFLOPS | Progress: (4/20) | 5.73 s
[Task 19/25] Current/Best: 13.50/ 21.11 GFLOPS | Progress: (8/20) | 8.65 s
[Task 19/25] Current/Best: 17.43/ 21.11 GFLOPS | Progress: (12/20) | 11.72 s
[Task 19/25] Current/Best: 6.11/ 21.11 GFLOPS | Progress: (16/20) | 14.74 s
[Task 19/25] Current/Best: 9.87/ 21.66 GFLOPS | Progress: (20/20) | 18.23 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.36/ 18.88 GFLOPS | Progress: (4/20) | 3.72 s
[Task 20/25] Current/Best: 10.34/ 20.58 GFLOPS | Progress: (8/20) | 6.18 s
[Task 20/25] Current/Best: 19.79/ 20.58 GFLOPS | Progress: (12/20) | 8.79 s
[Task 20/25] Current/Best: 14.07/ 20.58 GFLOPS | Progress: (16/20) | 13.07 s Done.
+
[Task 20/25] Current/Best: 12.23/ 20.58 GFLOPS | Progress: (20/20) | 19.60 s Done.
+
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 14.35/ 17.05 GFLOPS | Progress: (4/20) | 3.84 s
[Task 21/25] Current/Best: 16.44/ 17.05 GFLOPS | Progress: (8/20) | 5.47 s
[Task 21/25] Current/Best: 10.77/ 17.05 GFLOPS | Progress: (12/20) | 9.62 s
[Task 21/25] Current/Best: 8.48/ 18.45 GFLOPS | Progress: (16/20) | 13.48 s
[Task 21/25] Current/Best: 12.14/ 18.45 GFLOPS | Progress: (20/20) | 15.94 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.43/ 17.56 GFLOPS | Progress: (4/20) | 3.81 s
[Task 22/25] Current/Best: 10.45/ 17.56 GFLOPS | Progress: (8/20) | 6.45 s
[Task 22/25] Current/Best: 4.72/ 20.75 GFLOPS | Progress: (12/20) | 8.31 s
[Task 22/25] Current/Best: 6.62/ 20.75 GFLOPS | Progress: (16/20) | 10.13 s
[Task 22/25] Current/Best: 12.14/ 20.75 GFLOPS | Progress: (20/20)
| 11.92 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 22.54/ 22.54 GFLOPS | Progress: (4/20) | 4.21 s
[Task 23/25] Current/Best: 6.14/ 22.54 GFLOPS | Progress: (8/20) | 8.75 s
[Task 23/25] Current/Best: 11.17/ 22.54 GFLOPS | Progress: (12/20) | 12.52 s
[Task 23/25] Current/Best: 11.49/ 22.54 GFLOPS | Progress: (16/20) | 15.99 s
[Task 23/25] Current/Best: 19.08/ 22.54 GFLOPS | Progress: (20/20) | 19.13 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.90/ 7.90 GFLOPS | Progress: (4/20) | 8.25 s
[Task 24/25] Current/Best: 3.38/ 9.88 GFLOPS | Progress: (8/20) | 15.64 s
[Task 24/25] Current/Best: 3.48/ 9.88 GFLOPS | Progress: (12/20) | 26.60 s
[Task 24/25] Current/Best: 0.82/ 9.88 GFLOPS | Progress: (16/20) | 38.23 s Done.
+
[Task 24/25] Current/Best: 9.29/ 9.88 GFLOPS | Progress: (20/20) | 49.85 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.55/ 8.62 GFLOPS | Progress: (4/20) | 6.65 s
[Task 25/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (8/20) | 17.60 s
[Task 25/25] Current/Best: 6.28/ 8.72 GFLOPS | Progress: (12/20) | 28.27 s
[Task 25/25] Current/Best: 8.85/ 8.85 GFLOPS | Progress: (16/20) | 31.30 s
[Task 25/25] Current/Best: 1.57/ 8.85 GFLOPS | Progress: (20/20) | 41.69 s
@@ -664,8 +664,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621102
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -722,8 +722,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 404.32178098000804, 'median': 402.4068294999779, 'std': 3.5237674947711746}
- unoptimized: {'mean': 512.7073828600169, 'median': 513.0480596500092, 'std': 2.1568353339191852}
+ optimized: {'mean': 405.11662502000263, 'median': 405.1078924999956, 'std': 0.38688262390971795}
+ unoptimized: {'mean': 522.5552605600002, 'median': 522.2551564499952, 'std': 2.2707577388213855}
@@ -746,7 +746,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 47.439 seconds)
+ **Total running time of the script:** ( 11 minutes 56.490 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 6d4e3ab01c..d688bd660c 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.246e-07 secs/op
+ 1.234e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d4c1931314..1532eda862 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -268,7 +268,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x13767d10)), stage(b, placeholder(b, 0x21526e90)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T [...]
+ [stage(a, placeholder(a, 0x4fc4a30)), stage(b, placeholder(b, 0x2323cfc0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index bbb64b948a..cf2e7d784c 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**15:23.410** total execution time for **tutorial** files:
+**15:17.443** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:47.439 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:56.490 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:30.778 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:18.472 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.243 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.436 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.370 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.107 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:29.956 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.625 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.829 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.283 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.620 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.845 | 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``) | 00:00.185 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 27906f1b23..598848dbf8 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000006
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000024
@I.ir_module
class Module:
@T.prim_func
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.347210002990323e-06 1.0
- naive 6.6504e-06 0.905159917477965
- parallel 8.2623e-06 1.124549318263291
- vector 2.47094e-05 3.36309973308824
+ numpy 7.118900000477879e-06 1.0
+ naive 7.2542e-06 1.0190057452012304
+ parallel 6.062e-06 0.8515360518609714
+ vector 2.38004e-05 3.343269325092686
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018152
+ Numpy running time: 0.017604
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.205564
+ none: 3.335269
@@ -1077,7 +1077,7 @@ schedule.
.. code-block:: none
- blocking: 0.298386
+ blocking: 0.331104
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.335786
+ vectorization: 0.351840
@I.ir_module
class Module:
@T.prim_func
@@ -1221,7 +1221,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118068
+ loop permutation: 0.127500
@I.ir_module
class Module:
@T.prim_func
@@ -1309,7 +1309,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108872
+ array packing: 0.109420
@I.ir_module
class Module:
@T.prim_func
@@ -1389,7 +1389,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111419
+ block caching: 0.101913
@I.ir_module
class Module:
@T.prim_func
@@ -1460,7 +1460,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146252
+ parallelization: 0.135294
@I.ir_module
class Module:
@T.prim_func
@@ -1527,13 +1527,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2055641866999998 1.0
- blocking 0.2983864842 0.0930839212136248
- vectorization 0.3357857602 0.10475090830911672
- loop permutation 0.118068365 0.03683231971765528
- array packing 0.10887202059999998 0.03396345050637697
- block caching 0.11141909450000001 0.03475802947957861
- parallelization 0.14625249610000002 0.04562457264365719
+ none 3.3352686737999995 1.0
+ blocking 0.3311037549 0.09927348807038108
+ vectorization 0.35183957650000003 0.10549062486745205
+ loop permutation 0.12750047250000002 0.038227946522441277
+ array packing 0.1094195166 0.03280680727748813
+ block caching 0.10191306439999999 0.030556178337467047
+ parallelization 0.1352942509 0.040564723304840705
@@ -1573,6 +1573,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 0.436 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index bab0032793..fdfcde3eff 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-6fdb1b7e385efd1e296b94dd7f9fc2e0782b675a
+fd3f8035c94b31dbdbcce97864b1362ad254e4d1
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index ff77f818e4..5b70c23233 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.043 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.544 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 a024fa2cb9..bddff91fed 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 913ms/step
+1/1 [==============================] - 1s 1s/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 52f1f6f044..83d52fd1e9 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipcfa713df-1c84-4f10-ab81-733f5d3f2f4f 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.zipbb3a71ff-efef-4c42-8851-fa104a54ca26 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 1e42b35dde..a30c6ce50d 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,12 +449,14 @@ 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]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 69.4MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 68.1MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 62.2MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 68.3MB/s]
- 93%|#########3| 38.6M/41.5M [00:00<00:00, 53.7MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 58.6MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 39.4MB/s]
+ 24%|##4 | 10.1M/41.5M [00:00<00:00, 38.0MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 41.9MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 39.8MB/s]
+ 63%|######3 | 26.1M/41.5M [00:00<00:00, 32.1MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.4MB/s]
+ 91%|#########1| 37.9M/41.5M [00:00<00:00, 43.4MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 36.8MB/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 1df975f917..181d01e97e 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,11 +432,10 @@ 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]
- 15%|#4 | 6.60M/44.7M [00:00<00:00, 69.2MB/s]
- 36%|###5 | 15.9M/44.7M [00:00<00:00, 85.8MB/s]
- 68%|######7 | 30.3M/44.7M [00:00<00:00, 115MB/s]
- 92%|#########2| 41.3M/44.7M [00:00<00:00, 111MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 111MB/s]
+ 28%|##8 | 12.7M/44.7M [00:00<00:00, 133MB/s]
+ 57%|#####6 | 25.4M/44.7M [00:00<00:00, 112MB/s]
+ 81%|########1 | 36.2M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 108MB/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 ae7bb00f30..93ddf2c080 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.287 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.907 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 6668f39548..f9e83b1d62 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:18.324</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:39.827</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:20.287</p></td>
+<td><p>01:24.907</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>01:17.043</p></td>
+<td><p>01:21.544</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>00:51.560</p></td>
+<td><p>00:54.673</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>00:34.920</p></td>
+<td><p>00:37.635</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:30.693</p></td>
+<td><p>00:32.544</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:29.628</p></td>
+<td><p>00:31.625</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:26.575</p></td>
+<td><p>00:27.952</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:24.011</p></td>
+<td><p>00:24.675</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>00:20.928</p></td>
+<td><p>00:21.549</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>00:02.678</p></td>
+<td><p>00:02.725</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 0e162f8295..8ec428fe46 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2760.6683 2760.2357 2763.2731 2758.6312 1.3020
+ 2754.4563 2753.5079 2761.9300 2752.2152 2.7651
</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 a33654a131..81017547b8 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2175 16.3352 16.6377 15.6647 0.3352
+ 16.5539 16.3444 17.2734 16.2081 0.3907
</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 1ab3210a62..b742e4a6a1 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,33 +454,24 @@ 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]
- 1%|1 | 2.05M/170M [00:00<00:10, 17.3MB/s]
- 5%|4 | 7.99M/170M [00:00<00:05, 32.6MB/s]
- 9%|9 | 16.0M/170M [00:00<00:03, 51.3MB/s]
- 13%|#3 | 22.3M/170M [00:00<00:02, 52.0MB/s]
- 18%|#7 | 30.3M/170M [00:00<00:02, 56.1MB/s]
- 23%|##3 | 39.2M/170M [00:00<00:02, 66.8MB/s]
- 27%|##6 | 45.8M/170M [00:00<00:02, 63.3MB/s]
- 31%|### | 52.0M/170M [00:01<00:02, 46.8MB/s]
- 37%|###6 | 62.2M/170M [00:01<00:01, 60.4MB/s]
- 41%|#### | 68.9M/170M [00:01<00:01, 56.6MB/s]
- 44%|####4 | 75.0M/170M [00:01<00:01, 55.8MB/s]
- 48%|####7 | 80.7M/170M [00:01<00:01, 48.6MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 53.7MB/s]
- 57%|#####6 | 96.0M/170M [00:01<00:01, 55.2MB/s]
- 60%|#####9 | 102M/170M [00:02<00:01, 49.6MB/s]
- 63%|######2 | 106M/170M [00:02<00:01, 40.1MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 39.5MB/s]
- 71%|####### | 120M/170M [00:02<00:01, 49.2MB/s]
- 75%|#######4 | 127M/170M [00:02<00:00, 54.8MB/s]
- 78%|#######8 | 133M/170M [00:02<00:00, 54.3MB/s]
- 82%|########1 | 138M/170M [00:02<00:00, 54.6MB/s]
- 85%|########5 | 145M/170M [00:02<00:00, 57.2MB/s]
- 88%|########8 | 150M/170M [00:03<00:00, 47.3MB/s]
- 92%|#########1| 156M/170M [00:03<00:00, 49.5MB/s]
- 95%|#########4| 161M/170M [00:03<00:00, 45.6MB/s]
- 99%|#########8| 168M/170M [00:03<00:00, 50.8MB/s]
-100%|##########| 170M/170M [00:03<00:00, 51.5MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 67.4MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:01, 105MB/s]
+ 20%|## | 34.0M/170M [00:00<00:01, 88.5MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:01, 96.9MB/s]
+ 34%|###3 | 57.3M/170M [00:00<00:01, 77.6MB/s]
+ 39%|###9 | 66.6M/170M [00:00<00:01, 62.5MB/s]
+ 44%|####3 | 74.1M/170M [00:01<00:01, 54.0MB/s]
+ 48%|####8 | 82.1M/170M [00:01<00:01, 49.2MB/s]
+ 54%|#####4 | 92.4M/170M [00:01<00:01, 60.4MB/s]
+ 58%|#####8 | 99.0M/170M [00:01<00:01, 62.0MB/s]
+ 62%|######2 | 106M/170M [00:01<00:01, 58.8MB/s]
+ 67%|######7 | 114M/170M [00:01<00:00, 65.2MB/s]
+ 72%|#######1 | 122M/170M [00:01<00:00, 69.1MB/s]
+ 77%|#######6 | 130M/170M [00:02<00:00, 73.8MB/s]
+ 82%|########1 | 139M/170M [00:02<00:00, 64.7MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 71.1MB/s]
+ 97%|#########7| 165M/170M [00:02<00:00, 86.2MB/s]
+100%|##########| 170M/170M [00:02<00:00, 71.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -578,7 +569,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 25.499 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 41.745 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 6b35e6c552..01e2b7a7dc 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,8 +495,8 @@ 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]
- 47%|####7 | 6.38M/13.6M [00:00<00:00, 66.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 80.1MB/s]
+ 53%|#####3 | 7.21M/13.6M [00:00<00:00, 75.6MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 28.0MB/s]
</pre></div>
</div>
</div>
@@ -587,7 +587,7 @@ 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)
- 90.2753 90.1511 95.2123 90.0251 0.6409
+ 90.4976 90.4145 91.1622 90.2699 0.1995
</pre></div>
</div>
<div class="admonition note">
@@ -626,7 +626,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.487 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.588 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 65874b3787..34ce369827 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -580,7 +580,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.8064 120.7170 123.9868 120.0433 0.5117
+ 120.9403 120.8275 124.1355 120.1951 0.4916
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.980 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.066 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 fa3148bc33..2bd3365825 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 40.079 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.447 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 b576490a9f..9f9986f47d 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,25 +463,27 @@ 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]
- 2%|2 | 2671/132723 [00:00<00:04, 26706.97KB/s]
- 6%|5 | 7941/132723 [00:00<00:02, 41994.18KB/s]
- 12%|#1 | 15553/132723 [00:00<00:02, 57571.13KB/s]
- 18%|#7 | 23521/132723 [00:00<00:01, 66295.02KB/s]
- 24%|##3 | 31552/132723 [00:00<00:01, 71345.50KB/s]
- 30%|##9 | 39465/132723 [00:00<00:01, 73987.47KB/s]
- 36%|###5 | 47515/132723 [00:00<00:01, 76115.14KB/s]
- 42%|####1 | 55724/132723 [00:00<00:00, 78015.82KB/s]
- 48%|####7 | 63526/132723 [00:00<00:01, 62257.87KB/s]
- 53%|#####3 | 70636/132723 [00:01<00:00, 64579.06KB/s]
- 59%|#####8 | 77946/132723 [00:01<00:00, 66902.63KB/s]
- 64%|######4 | 85079/132723 [00:01<00:00, 68143.72KB/s]
- 69%|######9 | 92105/132723 [00:01<00:00, 67725.12KB/s]
- 75%|#######4 | 99025/132723 [00:01<00:00, 60682.27KB/s]
- 79%|#######9 | 105318/132723 [00:01<00:00, 57615.21KB/s]
- 85%|########5 | 113138/132723 [00:01<00:00, 63054.67KB/s]
- 91%|#########1| 121148/132723 [00:01<00:00, 67722.64KB/s]
- 97%|#########7| 129144/132723 [00:01<00:00, 71163.28KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 66441.67KB/s]
+ 1%| | 917/132723 [00:00<00:14, 9089.09KB/s]
+ 2%|2 | 2761/132723 [00:00<00:09, 14244.02KB/s]
+ 5%|4 | 6054/132723 [00:00<00:05, 22653.45KB/s]
+ 8%|8 | 10872/132723 [00:00<00:03, 32642.13KB/s]
+ 13%|#3 | 17849/132723 [00:00<00:02, 45949.23KB/s]
+ 20%|#9 | 26338/132723 [00:00<00:01, 59136.72KB/s]
+ 24%|##4 | 32268/132723 [00:00<00:01, 59169.23KB/s]
+ 31%|### | 40814/132723 [00:00<00:01, 67521.31KB/s]
+ 37%|###6 | 48944/132723 [00:00<00:01, 71821.07KB/s]
+ 42%|####2 | 56133/132723 [00:01<00:01, 64463.19KB/s]
+ 48%|####7 | 63696/132723 [00:01<00:01, 67622.68KB/s]
+ 54%|#####3 | 71197/132723 [00:01<00:00, 69748.74KB/s]
+ 59%|#####9 | 78737/132723 [00:01<00:00, 71386.12KB/s]
+ 65%|######4 | 85951/132723 [00:01<00:00, 59053.82KB/s]
+ 70%|####### | 93348/132723 [00:01<00:00, 62889.98KB/s]
+ 76%|#######5 | 100678/132723 [00:01<00:00, 65685.34KB/s]
+ 82%|########1 | 108199/132723 [00:01<00:00, 68326.51KB/s]
+ 87%|########7 | 115680/132723 [00:01<00:00, 70164.36KB/s]
+ 93%|#########2| 122856/132723 [00:02<00:00, 68917.17KB/s]
+ 98%|#########8| 130370/132723 [00:02<00:00, 70696.70KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 61632.46KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -520,7 +522,7 @@ 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 33.266 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 46.028 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 28a9db9300..53fb0c3d8a 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:53.085</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>15:44.868</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:33.266</p></td>
+<td><p>03:46.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:25.499</p></td>
+<td><p>03:41.745</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>02:30.980</p></td>
+<td><p>02:30.066</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>01:40.079</p></td>
+<td><p>01:53.447</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:13.487</p></td>
+<td><p>01:17.588</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>00:56.086</p></td>
+<td><p>00:57.310</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:40.338</p></td>
+<td><p>00:42.938</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>00:26.926</p></td>
+<td><p>00:28.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:26.418</p></td>
+<td><p>00:27.638</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 073255247c..91c49efa4d 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -619,7 +619,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip503b1a7b-8a58-4993-ba83-e53a434e2c63 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.zip615ebc50-9255-4590-8c3a-4b2e64134aff 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 b1c8d8a70f..a3cfc0a6c5 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:52.337</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:55.765</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:48.556</p></td>
+<td><p>00:51.846</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>00:02.692</p></td>
+<td><p>00:02.802</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>00:01.083</p></td>
+<td><p>00:01.111</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index e3b455195c..c5377e9808 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 20835us [20835us] (47.62%; 47.62%)
-FoldScaleAxis: 22922us [8us] (52.38%; 52.38%)
- FoldConstant: 22914us [1732us] (52.37%; 99.97%)
- InferType: 21182us [21182us] (48.41%; 92.44%)
+InferType: 21196us [21196us] (48.34%; 48.34%)
+FoldScaleAxis: 22654us [9us] (51.66%; 51.66%)
+ FoldConstant: 22645us [1771us] (51.64%; 99.96%)
+ InferType: 20874us [20874us] (47.60%; 92.18%)
</pre></div>
</div>
</div>
@@ -551,10 +551,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 20405us [20405us] (48.09%; 48.09%)
-FoldScaleAxis: 22029us [7us] (51.91%; 51.91%)
- FoldConstant: 22022us [1742us] (51.90%; 99.97%)
- InferType: 20280us [20280us] (47.79%; 92.09%)
+InferType: 20944us [20944us] (48.07%; 48.07%)
+FoldScaleAxis: 22628us [8us] (51.93%; 51.93%)
+ FoldConstant: 22620us [1819us] (51.91%; 99.97%)
+ InferType: 20801us [20801us] (47.74%; 91.96%)
</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 21bc1d969a..f8a93beeaf 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -575,7 +575,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 39.953472 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.765216 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 901937ba9f..5121eded22 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -861,7 +861,7 @@ 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: 13.364519 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.789965 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 ab319a6f98..24f2af333b 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -472,8 +472,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018115
-Baseline: 3.214453
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019491
+Baseline: 3.326171
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -529,7 +529,7 @@ 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: 0.296729
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.326349
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -583,7 +583,7 @@ 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: 0.328841
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.346240
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -635,7 +635,7 @@ 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: 0.114458
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.130476
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -709,7 +709,7 @@ 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: 0.109586
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110579
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -784,7 +784,7 @@ 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: 0.111330
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112296
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -861,7 +861,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147028
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148557
</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 823552647b..32233b53a5 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.282</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.717</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.536</p></td>
+<td><p>00:32.912</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>00:01.596</p></td>
+<td><p>00:01.633</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>00:01.150</p></td>
+<td><p>00:01.172</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 565f849e41..1612e33dfe 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:20.255</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:49.224</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:36.116</p></td>
+<td><p>06:01.402</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>01:39.221</p></td>
+<td><p>01:42.322</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>01:05.990</p></td>
+<td><p>01:08.143</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>00:31.691</p></td>
+<td><p>00:28.685</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:14.177</p></td>
+<td><p>00:15.017</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>00:13.059</p></td>
+<td><p>00:13.655</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 2f8e820b50..ebc8346753 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
@@ -503,481 +503,760 @@ class Module:
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 28)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([72], "float32", "shared")
- kernel_shared = T.allocate([3072], "float32", "shared")
+ T.launch_thread(blockIdx_x, 128)
+ conv2d_nchw = T.allocate([2], "float32", "local")
+ pad_temp_shared = T.allocate([2016], "float32", "shared")
+ kernel_shared = T.allocate([384], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 64)
- conv2d_nchw_1 = T.buffer_decl((14,), data=conv2d_nchw, scope="local", align=32)
+ T.launch_thread(threadIdx_x, 98)
+ conv2d_nchw_1 = T.buffer_decl((2,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(64, 3):
- cse_var_2: T.int32 = rc_outer_outer * 72
- cse_var_1: T.int32 = ry_outer_outer * 3
+ for rc_outer_outer in range(16):
+ cse_var_2: T.int32 = rc_outer_outer * 1568
+ cse_var_1: T.int32 = rc_outer_outer * 288
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.buffer_decl((72,), data=pad_temp_shared, scope="shared")
- with T.launch_thread(threadIdx_x_1, 64):
- data_1 = T.buffer_decl((25088,), data=data.data)
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 * 4 % 9 and threadIdx_x_1 * 4 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 * 4 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 * 4 % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 1) % 9 and (threadIdx_x_1 * 4 + 1) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 1) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 1) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 2] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 2) % 9 and (threadIdx_x_1 * 4 + 2) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 2) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 2) % 9 - 8], T.float32(0))
- if T.likely(threadIdx_x_1 < 18):
- pad_temp_shared_1[threadIdx_x_1 * 4 + 3] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 3) % 9 and (threadIdx_x_1 * 4 + 3) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 3) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1 = T.buffer_decl((2016,), data=pad_temp_shared, scope="shared")
+ data_1 = T.buffer_decl((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 63 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(9 <= (threadIdx_x_1 + 35) % 63 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(9 <= (threadIdx_x_1 + 7) % 63 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(9 <= (threadIdx_x_1 + 42) % 63 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(9 <= (threadIdx_x_1 + 14) % 63 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(9 <= (threadIdx_x_1 + 49) % 63 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(9 <= (threadIdx_x_1 + 21) % 63 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(9 <= (threadIdx_x_1 + 56) % 63 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(9 <= (threadIdx_x_1 + 28) % 63 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(9 <= threadIdx_x_1 % 63 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 678], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(9 <= (threadIdx_x_1 + 35) % 63 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(9 <= (threadIdx_x_1 + 7) % 63 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(9 <= (threadIdx_x_1 + 42) % 63 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(9 <= (threadIdx_x_1 + 14) % 63 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else(9 <= (threadIdx_x_1 + 49) % 63 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else(9 <= (threadIdx_x_1 + 21) % 63 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(9 <= (threadIdx_x_1 + 56) % 63 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else(9 <= (threadIdx_x_1 + 28) % 63 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(9 <= threadIdx_x_1 % 63 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 1364], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else(9 <= (threadIdx_x_1 + 35) % 63 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ if T.likely(threadIdx_x_1 < 56):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else(9 <= (threadIdx_x_1 + 7) % 63 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.buffer_decl((3072,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.buffer_decl((384,), data=kernel_shared, scope="shared")
kernel_1 = T.buffer_decl((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 64] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 128] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 192] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 256] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 320] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 384] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 512] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 576] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 640] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 704] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 768] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 832] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 960] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1024] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1088] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1152] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1216] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1280] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1408] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1472] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1536] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 294912]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1600] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1664] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1728] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 331776]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1792] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1856] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1920] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 368640]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 1984] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2048] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2112] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 405504]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2176] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2240] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2304] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 442368]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2368] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2432] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2496] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 479232]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2560] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2624] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 516096]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2752] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2816] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2880] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 552960]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 2944] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 64):
- kernel_shared_1[threadIdx_x_2 + 3008] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 3]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 24]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 27]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 1]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 4]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 25]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 28]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 2]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 5]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 26]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 29]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 6]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 9]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 30]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 33]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 7]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 10]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 31]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 34]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 8]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 11]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 32]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 35]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 12]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 15]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 36]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 39]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 13]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 16]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 37]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 40]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 14]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 17]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 38]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 41]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 18]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 21]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 42]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 45]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 19]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 22]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 43]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 46]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 20]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 23]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 47]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 44]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 47]
- for i1_inner, i3_inner in T.grid(2, 7):
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 96 * 4608 + cse_var_1 + threadIdx_x_2 % 96 // 3 * 9 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 98) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 96 // 3 * 9 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 196) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 96 // 3 * 9 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ if T.likely(threadIdx_x_2 < 90):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 294) // 96 * 4608 + cse_var_1 + threadIdx_x_2 // 3 * 9 + threadIdx_x_2 % 3 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 102]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 105]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 108]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 111]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 114]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 117]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 120]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 27]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 123]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 30]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 126]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 33]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 129]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 132]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 39]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 135]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 42]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 138]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 97]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 103]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 106]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 109]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 112]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 115]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 118]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 25]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 121]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 28]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 124]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 31]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 127]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 34]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 130]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 37]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 133]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 40]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 136]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 43]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 139]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 98]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 101]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 104]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 107]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 110]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 113]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 116]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 119]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 26]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 122]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 29]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 125]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 32]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 128]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 35]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 131]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 38]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 134]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 41]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 137]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 44]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 140]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 143]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 144]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 147]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 150]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 153]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 156]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 159]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 168]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 171]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 174]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 177]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 180]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 183]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 186]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 93]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 189]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 145]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 148]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 151]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 154]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 157]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 169]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 172]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 175]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 178]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 181]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 184]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 187]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 94]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 190]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 146]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 149]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 152]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 155]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 158]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 170]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 173]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 176]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 179]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 182]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 185]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 188]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 95]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 191]
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 685], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else(1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 1371], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ if T.likely(threadIdx_x_1 < 56):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else(1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 1], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 96 * 4608 + cse_var_1 + threadIdx_x_2 % 96 // 3 * 9 + threadIdx_x_2 % 3 + 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 98) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 96 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 196) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 96 // 3 * 9 + (threadIdx_x_2 + 1) % 3 + 3]
+ with T.launch_thread(threadIdx_x_2, 98):
+ if T.likely(threadIdx_x_2 < 90):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 294) // 96 * 4608 + cse_var_1 + threadIdx_x_2 // 3 * 9 + threadIdx_x_2 % 3 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 102]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 105]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 108]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 111]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 114]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 117]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 120]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 27]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 123]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 30]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 126]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 33]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 129]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 132]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 39]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 135]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 42]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 138]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 97]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 103]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 106]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 109]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 112]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 115]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 118]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 25]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 121]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 28]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 124]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 31]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 127]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 34]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 130]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 37]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 133]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 40]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 136]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 43]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 139]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 98]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 101]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 104]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 107]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 110]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 113]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 116]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 119]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 26]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 122]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 29]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 125]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 32]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 128]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 35]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 131]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 38]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 134]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 41]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 137]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 44]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 140]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 143]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 144]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 147]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 150]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 153]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 156]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 159]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 168]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 171]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 174]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 177]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 180]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 183]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 186]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 93]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 189]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 145]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 148]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 151]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 154]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 157]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 169]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 172]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 175]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 178]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 181]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 184]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 187]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 94]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 190]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 146]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 149]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 152]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 155]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 158]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 170]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 173]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 176]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 179]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 182]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 185]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 188]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 95]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 191]
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(threadIdx_x_1 % 63 < 54 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else((threadIdx_x_1 + 35) % 63 < 54 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else((threadIdx_x_1 + 7) % 63 < 54 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else((threadIdx_x_1 + 42) % 63 < 54 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 9 * 7 + (threadIdx_x_1 + 6) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else((threadIdx_x_1 + 14) % 63 < 54 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 9 * 7 + (threadIdx_x_1 + 5) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else((threadIdx_x_1 + 49) % 63 < 54 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 9 * 7 + (threadIdx_x_1 + 4) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else((threadIdx_x_1 + 21) % 63 < 54 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 9 * 7 + (threadIdx_x_1 + 3) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else((threadIdx_x_1 + 56) % 63 < 54 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 9 * 7 + (threadIdx_x_1 + 2) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else((threadIdx_x_1 + 28) % 63 < 54 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 9 * 7 + (threadIdx_x_1 + 1) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(threadIdx_x_1 % 63 < 54 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 692], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else((threadIdx_x_1 + 35) % 63 < 54 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else((threadIdx_x_1 + 7) % 63 < 54 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else((threadIdx_x_1 + 42) % 63 < 54 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 9 * 7 + (threadIdx_x_1 + 6) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else((threadIdx_x_1 + 14) % 63 < 54 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 9 * 7 + (threadIdx_x_1 + 5) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1372] = T.if_then_else((threadIdx_x_1 + 49) % 63 < 54 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1372) // 9 * 7 + (threadIdx_x_1 + 4) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1470] = T.if_then_else((threadIdx_x_1 + 21) % 63 < 54 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1470) // 9 * 7 + (threadIdx_x_1 + 3) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1568] = T.if_then_else((threadIdx_x_1 + 56) % 63 < 54 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1568) // 9 * 7 + (threadIdx_x_1 + 2) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1666] = T.if_then_else((threadIdx_x_1 + 28) % 63 < 54 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1666) // 9 * 7 + (threadIdx_x_1 + 1) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1764] = T.if_then_else(threadIdx_x_1 % 63 < 54 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 + 1378], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ pad_temp_shared_1[threadIdx_x_1 + 1862] = T.if_then_else((threadIdx_x_1 + 35) % 63 < 54 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1862) // 9 * 7 + (threadIdx_x_1 + 8) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 98):
+ if T.likely(threadIdx_x_1 < 56):
+ pad_temp_shared_1[threadIdx_x_1 + 1960] = T.if_then_else((threadIdx_x_1 + 7) % 63 < 54 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1960) // 9 * 7 + (threadIdx_x_1 + 7) % 9 + 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 18432 + threadIdx_x_2 // 96 * 4608 + cse_var_1 + threadIdx_x_2 % 96 // 3 * 9 + threadIdx_x_2 % 3 + 6]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 98) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 96 // 3 * 9 + (threadIdx_x_2 + 2) % 3 + 6]
+ with T.launch_thread(threadIdx_x_2, 98):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 196) // 96 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 96 // 3 * 9 + (threadIdx_x_2 + 1) % 3 + 6]
+ with T.launch_thread(threadIdx_x_2, 98):
+ if T.likely(threadIdx_x_2 < 90):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_2 + 294) // 96 * 4608 + cse_var_1 + threadIdx_x_2 // 3 * 9 + threadIdx_x_2 % 3 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 192 + 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 49 * 192 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 49 * 192 + 102]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 49 * 192 + 105]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 49 * 192 + 108]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 49 * 192 + 111]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 49 * 192 + 114]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 49 * 192 + 117]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 504] * kernel_shared_1[threadIdx_x // 49 * 192 + 120]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 27]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 49 * 192 + 123]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 30]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 630] * kernel_shared_1[threadIdx_x // 49 * 192 + 126]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 33]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 693] * kernel_shared_1[threadIdx_x // 49 * 192 + 129]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 756] * kernel_shared_1[threadIdx_x // 49 * 192 + 132]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 39]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 819] * kernel_shared_1[threadIdx_x // 49 * 192 + 135]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 42]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 882] * kernel_shared_1[threadIdx_x // 49 * 192 + 138]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 945] * kernel_shared_1[threadIdx_x // 49 * 192 + 141]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 192 + 97]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 49 * 192 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 49 * 192 + 103]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 49 * 192 + 106]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 49 * 192 + 109]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 49 * 192 + 112]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 49 * 192 + 115]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 49 * 192 + 118]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 25]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 505] * kernel_shared_1[threadIdx_x // 49 * 192 + 121]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 28]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 568] * kernel_shared_1[threadIdx_x // 49 * 192 + 124]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 31]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 631] * kernel_shared_1[threadIdx_x // 49 * 192 + 127]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 34]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 694] * kernel_shared_1[threadIdx_x // 49 * 192 + 130]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 37]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 757] * kernel_shared_1[threadIdx_x // 49 * 192 + 133]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 40]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 820] * kernel_shared_1[threadIdx_x // 49 * 192 + 136]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 43]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 883] * kernel_shared_1[threadIdx_x // 49 * 192 + 139]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 946] * kernel_shared_1[threadIdx_x // 49 * 192 + 142]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 192 + 98]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 49 * 192 + 101]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 49 * 192 + 104]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 49 * 192 + 107]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 49 * 192 + 110]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 49 * 192 + 113]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 49 * 192 + 116]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 49 * 192 + 119]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 26]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 506] * kernel_shared_1[threadIdx_x // 49 * 192 + 122]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 29]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 569] * kernel_shared_1[threadIdx_x // 49 * 192 + 125]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 32]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 632] * kernel_shared_1[threadIdx_x // 49 * 192 + 128]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 35]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 695] * kernel_shared_1[threadIdx_x // 49 * 192 + 131]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 38]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 758] * kernel_shared_1[threadIdx_x // 49 * 192 + 134]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 41]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 821] * kernel_shared_1[threadIdx_x // 49 * 192 + 137]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 44]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 884] * kernel_shared_1[threadIdx_x // 49 * 192 + 140]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 947] * kernel_shared_1[threadIdx_x // 49 * 192 + 143]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1008] * kernel_shared_1[threadIdx_x // 49 * 192 + 144]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1071] * kernel_shared_1[threadIdx_x // 49 * 192 + 147]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1134] * kernel_shared_1[threadIdx_x // 49 * 192 + 150]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1197] * kernel_shared_1[threadIdx_x // 49 * 192 + 153]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1260] * kernel_shared_1[threadIdx_x // 49 * 192 + 156]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1323] * kernel_shared_1[threadIdx_x // 49 * 192 + 159]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1386] * kernel_shared_1[threadIdx_x // 49 * 192 + 162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1449] * kernel_shared_1[threadIdx_x // 49 * 192 + 165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1512] * kernel_shared_1[threadIdx_x // 49 * 192 + 168]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1575] * kernel_shared_1[threadIdx_x // 49 * 192 + 171]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1638] * kernel_shared_1[threadIdx_x // 49 * 192 + 174]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1701] * kernel_shared_1[threadIdx_x // 49 * 192 + 177]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1764] * kernel_shared_1[threadIdx_x // 49 * 192 + 180]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1827] * kernel_shared_1[threadIdx_x // 49 * 192 + 183]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1890] * kernel_shared_1[threadIdx_x // 49 * 192 + 186]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 93]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1953] * kernel_shared_1[threadIdx_x // 49 * 192 + 189]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1009] * kernel_shared_1[threadIdx_x // 49 * 192 + 145]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1072] * kernel_shared_1[threadIdx_x // 49 * 192 + 148]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1135] * kernel_shared_1[threadIdx_x // 49 * 192 + 151]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1198] * kernel_shared_1[threadIdx_x // 49 * 192 + 154]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1261] * kernel_shared_1[threadIdx_x // 49 * 192 + 157]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1324] * kernel_shared_1[threadIdx_x // 49 * 192 + 160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1387] * kernel_shared_1[threadIdx_x // 49 * 192 + 163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1450] * kernel_shared_1[threadIdx_x // 49 * 192 + 166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1513] * kernel_shared_1[threadIdx_x // 49 * 192 + 169]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1576] * kernel_shared_1[threadIdx_x // 49 * 192 + 172]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1639] * kernel_shared_1[threadIdx_x // 49 * 192 + 175]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1702] * kernel_shared_1[threadIdx_x // 49 * 192 + 178]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1765] * kernel_shared_1[threadIdx_x // 49 * 192 + 181]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1828] * kernel_shared_1[threadIdx_x // 49 * 192 + 184]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1891] * kernel_shared_1[threadIdx_x // 49 * 192 + 187]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 94]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1954] * kernel_shared_1[threadIdx_x // 49 * 192 + 190]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1010] * kernel_shared_1[threadIdx_x // 49 * 192 + 146]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1073] * kernel_shared_1[threadIdx_x // 49 * 192 + 149]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1136] * kernel_shared_1[threadIdx_x // 49 * 192 + 152]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1199] * kernel_shared_1[threadIdx_x // 49 * 192 + 155]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1262] * kernel_shared_1[threadIdx_x // 49 * 192 + 158]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1325] * kernel_shared_1[threadIdx_x // 49 * 192 + 161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1388] * kernel_shared_1[threadIdx_x // 49 * 192 + 164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1451] * kernel_shared_1[threadIdx_x // 49 * 192 + 167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1514] * kernel_shared_1[threadIdx_x // 49 * 192 + 170]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1577] * kernel_shared_1[threadIdx_x // 49 * 192 + 173]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1640] * kernel_shared_1[threadIdx_x // 49 * 192 + 176]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1703] * kernel_shared_1[threadIdx_x // 49 * 192 + 179]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1766] * kernel_shared_1[threadIdx_x // 49 * 192 + 182]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1829] * kernel_shared_1[threadIdx_x // 49 * 192 + 185]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1892] * kernel_shared_1[threadIdx_x // 49 * 192 + 188]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 95]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 49 // 7 * 9 + threadIdx_x % 7 + 1955] * kernel_shared_1[threadIdx_x // 49 * 192 + 191]
+ for i1_inner in range(2):
compute_1 = T.buffer_decl((25088,), data=compute.data)
bias_1 = T.buffer_decl((512,), data=bias.data)
- compute_1[blockIdx_x // 7 * 6272 + threadIdx_x * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 196 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 4 + threadIdx_x // 49 * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -1011,7 +1290,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.357 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.353 ms
</pre></div>
</div>
</div>
@@ -1040,20 +1319,20 @@ 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=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
@@ -1063,13 +1342,13 @@ compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, 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)
@@ -1089,14 +1368,14 @@ 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=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1114,430 +1393,685 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[384];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((9 <= ((((int)threadIdx.x) + 7) % 63)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((9 <= ((((int)threadIdx.x) + 42) % 63)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((9 <= ((((int)threadIdx.x) + 14) % 63)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((9 <= ((((int)threadIdx.x) + 49) % 63)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((9 <= ((((int)threadIdx.x) + 21) % 63)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = ((((9 <= ((((int)threadIdx.x) + 56) % 63)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((9 <= ((((int)threadIdx.x) + 28) % 63)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((9 <= ((((int)threadIdx.x) + 7) % 63)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((9 <= ((((int)threadIdx.x) + 42) % 63)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((9 <= ((((int)threadIdx.x) + 14) % 63)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((9 <= ((((int)threadIdx.x) + 49) % 63)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = ((((9 <= ((((int)threadIdx.x) + 21) % 63)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((9 <= ((((int)threadIdx.x) + 56) % 63)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = ((((9 <= ((((int)threadIdx.x) + 28) % 63)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = ((((2 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 90) {
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 18)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 685)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((1 <= ((((int)threadIdx.x) + 6) % 9)) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 1371)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 1) % 3)) + 3)];
+ if (((int)threadIdx.x) < 90) {
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 21)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((((int)threadIdx.x) + 7) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((((((int)threadIdx.x) + 42) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((((int)threadIdx.x) + 14) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((((((int)threadIdx.x) + 49) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((((int)threadIdx.x) + 21) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = ((((((((int)threadIdx.x) + 56) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((((((int)threadIdx.x) + 28) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 692)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((((int)threadIdx.x) + 7) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = ((((((((int)threadIdx.x) + 42) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((((int)threadIdx.x) + 14) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = ((((((((int)threadIdx.x) + 49) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = ((((((((int)threadIdx.x) + 21) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((((((int)threadIdx.x) + 56) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = ((((((((int)threadIdx.x) + 28) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 1378)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 18432) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 2) % 3)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + ((((int)threadIdx.x) + 1) % 3)) + 6)];
+ if (((int)threadIdx.x) < 90) {
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (((int)threadIdx.x) % 3)) + 24)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 4) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1574,7 +2108,7 @@ 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 36.116 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 1.402 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 12af359ddd..3e66c2ee82 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9267 7.9273 7.9405 7.9122 0.0115
+ 7.8978 7.8994 7.9028 7.8912 0.0049
</pre></div>
</div>
</div>
@@ -938,7 +938,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.990 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.143 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 5c26c96449..d65b4ef020 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 758.1683 758.4689 759.1544 756.8816 0.9519
+ 756.8337 756.6105 758.7611 755.1294 1.4910
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 39.221 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.322 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 4147546d69..1f38bbf6bc 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -629,74 +629,26 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.buffer_decl((1024,), data=compute_1)
- for nb_j_inner in range(2):
- for i_inner_init in range(32):
- cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
- compute_2[cse_var_1] = T.float32(0)
- compute_2[cse_var_1 + 1] = T.float32(0)
- compute_2[cse_var_1 + 2] = T.float32(0)
- compute_2[cse_var_1 + 3] = T.float32(0)
- compute_2[cse_var_1 + 4] = T.float32(0)
- compute_2[cse_var_1 + 5] = T.float32(0)
- compute_2[cse_var_1 + 6] = T.float32(0)
- compute_2[cse_var_1 + 7] = T.float32(0)
- compute_2[cse_var_1 + 8] = T.float32(0)
- compute_2[cse_var_1 + 9] = T.float32(0)
- compute_2[cse_var_1 + 10] = T.float32(0)
- compute_2[cse_var_1 + 11] = T.float32(0)
- compute_2[cse_var_1 + 12] = T.float32(0)
- compute_2[cse_var_1 + 13] = T.float32(0)
- compute_2[cse_var_1 + 14] = T.float32(0)
- compute_2[cse_var_1 + 15] = T.float32(0)
- for elem_idx, i_inner in T.grid(T.let(cse_var_2, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 32):
- cse_var_2 = T.var("int32")
+ for i0_outer_i1_outer_fused in T.parallel(16):
+ compute_1 = T.allocate([4096], "float32", "global")
+ compute_2 = T.buffer_decl((4096,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(32, 2):
+ for i_inner_init, j_init in T.grid(4, 16):
+ compute_2[i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.let(cse_var_1, i0_outer_i1_outer_fused * 2 + nb_j_inner, placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]), 4, 16):
+ cse_var_1 = T.var("int32")
placeholder_5 = T.buffer_decl((33,), "int32", data=placeholder_3.data)
- cse_var_21: T.int32 = elem_idx * 16
- cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
- cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i_inner * 256
- cse_var_17: T.int32 = cse_var_20 + 9
- cse_var_16: T.int32 = cse_var_20 + 8
- cse_var_15: T.int32 = cse_var_20 + 7
- cse_var_14: T.int32 = cse_var_20 + 6
- cse_var_13: T.int32 = cse_var_20 + 5
- cse_var_12: T.int32 = cse_var_20 + 4
- cse_var_11: T.int32 = cse_var_20 + 3
- cse_var_10: T.int32 = cse_var_20 + 2
- cse_var_9: T.int32 = cse_var_20 + 15
- cse_var_8: T.int32 = cse_var_20 + 14
- cse_var_7: T.int32 = cse_var_20 + 13
- cse_var_6: T.int32 = cse_var_20 + 12
- cse_var_5: T.int32 = cse_var_20 + 11
- cse_var_4: T.int32 = cse_var_20 + 10
- cse_var_3: T.int32 = cse_var_20 + 1
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.buffer_decl((78656,), data=placeholder_1.data)
placeholder_7 = T.buffer_decl((32768,), data=placeholder.data)
placeholder_8 = T.buffer_decl((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- for i0_inner, i1_inner in T.grid(32, 32):
- cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i_outer_inner * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(128, 32):
+ cse_var_4: T.int32 = i0_inner * 512 + i0_outer_i1_outer_fused * 32 + i1_inner
compute_3 = T.buffer_decl((65536,), data=compute.data)
placeholder_5 = T.buffer_decl((65536,), data=placeholder_4.data)
- compute_3[cse_var_22] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_22], T.float32(0))
+ compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
</pre></div>
</div>
</div>
@@ -730,7 +682,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.754 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.475 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 509eed018e..a34941fffc 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:26.869</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:30.121</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:26.835</p></td>
+<td><p>00:30.087</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 3c78de3e9b..7b702bf576 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -690,8 +690,9 @@ 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, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2214411
-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, 8, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8688131
+No: 2 GFLOPS: 3.47/3.47 result: MeasureResult(costs=(0.06669478599999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.769287347793579, timestamp=1674607135.604493) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6206840
+No: 3 GFLOPS: 0.00/3.47 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
@@ -813,8 +814,8 @@ 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, 16, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2836600
-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, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,87647
+No: 4 GFLOPS: 0.00/3.47 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
@@ -936,8 +937,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3432632
-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, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9995123
+No: 5 GFLOPS: 0.00/3.47 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
@@ -1059,8 +1060,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1447163
-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, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8624261
+No: 6 GFLOPS: 0.00/3.47 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
@@ -1182,8 +1183,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6784467
-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, 32, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4967045
+No: 7 GFLOPS: 0.00/3.47 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
@@ -1305,8 +1306,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1826993
-No: 7 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, 4, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2252786
+No: 8 GFLOPS: 72.15/72.15 result: MeasureResult(costs=(0.0032085432790697676,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.026492118835449, timestamp=1674607139.8619287) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4138423
+No: 9 GFLOPS: 192.90/192.90 result: MeasureResult(costs=(0.0012000854056603773,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.224464178085327, timestamp=1674607142.2581093) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4666258
+No: 10 GFLOPS: 0.00/192.90 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
@@ -1428,8 +1431,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4946347
-No: 8 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, 1, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,946830
+No: 11 GFLOPS: 7.34/192.90 result: MeasureResult(costs=(0.0315600965,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3601210117340088, timestamp=1674607143.089132) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5634830
+No: 12 GFLOPS: 0.00/192.90 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
@@ -1551,8 +1555,8 @@ 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, 1, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5782830
-No: 9 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, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,642790
+No: 13 GFLOPS: 0.00/192.90 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
@@ -1674,8 +1678,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4312082
-No: 10 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, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1470120
+No: 14 GFLOPS: 0.00/192.90 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
@@ -1797,8 +1801,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4059898
-No: 11 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, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,906292
+No: 15 GFLOPS: 0.00/192.90 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
@@ -1920,8 +1924,9 @@ 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, 16, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8588314
-No: 12 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, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5110594
+No: 16 GFLOPS: 5.50/192.90 result: MeasureResult(costs=(0.042091648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.724987268447876, timestamp=1674607146.0543864) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8018703
+No: 17 GFLOPS: 0.00/192.90 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
@@ -2043,8 +2048,8 @@ 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, 1, 16, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4180378
-No: 13 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, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2504378
+No: 18 GFLOPS: 0.00/192.90 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
@@ -2166,9 +2171,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1613938
-No: 14 GFLOPS: 67.22/67.22 result: MeasureResult(costs=(0.0034440511,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.426131010055542, timestamp=1674597919.1928568) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5338876
-No: 15 GFLOPS: 0.00/67.22 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,753752
+No: 19 GFLOPS: 0.00/192.90 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
@@ -2290,8 +2294,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4238664
-No: 16 GFLOPS: 0.00/67.22 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, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1130988
+No: 20 GFLOPS: 0.00/192.90 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
@@ -2413,255 +2417,7 @@ 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, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6831409
-No: 17 GFLOPS: 6.32/67.22 result: MeasureResult(costs=(0.036649433,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.555211544036865, timestamp=1674597923.9573052) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8132850
-No: 18 GFLOPS: 8.31/67.22 result: MeasureResult(costs=(0.027861503500000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5806710720062256, timestamp=1674597924.7226763) [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5490176
-No: 19 GFLOPS: 0.00/67.22 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3785226
-No: 20 GFLOPS: 0.00/67.22 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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:395
- 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:381
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:276
- 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:451
- 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, 16, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3839999
+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, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2357860
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2700,9 +2456,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5338876
+[('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4666258
Finish loading 20 records
-Time cost of this operator: 0.003815
+Time cost of this operator: 0.001368
</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 7b47dc6cca..9079062ff2 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -647,10 +647,10 @@ 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 312.5 98.728 (1, 2, 10, 10, 3) 2 1 [312.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.961 (1, 6, 10, 10) 1 1 [3.042]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.985 0.311 (1, 1, 10, 10, 3) 1 1 [0.985]
-Total_time - 316.528 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.727 (1, 2, 10, 10, 3) 2 1 [309.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.028 0.965 (1, 6, 10, 10) 1 1 [3.028]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.307 (1, 1, 10, 10, 3) 1 1 [0.963]
+Total_time - 313.591 - - - - -
</pre></div>
</div>
</div>
@@ -702,10 +702,10 @@ 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 102.9 97.492 (1, 6, 10, 10, 1) 2 1 [102.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.783 1.69 (1, 6, 10, 10) 1 1 [1.783]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.864 0.819 (1, 3, 10, 10, 1) 1 1 [0.864]
-Total_time - 105.548 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.2 97.421 (1, 6, 10, 10, 1) 2 1 [103.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.761 1.662 (1, 6, 10, 10) 1 1 [1.761]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.917 (1, 1, 10, 10, 3) 1 1 [0.972]
+Total_time - 105.932 - - - - -
</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 3997b3c25f..3ac46256a9 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -454,7 +454,8 @@ 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, 36.5MB/s]
+ 61%|###### | 2.09M/3.42M [00:00<00:00, 18.1MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 28.3MB/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.
@@ -578,7 +579,7 @@ 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 9.962 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.935 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 8140766e31..f93c198f6d 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/tmp5gq4omcf/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpv5rhl63h/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="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp5gq4omcf/images/target contains 8144 images
-/tmp/tmp5gq4omcf/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpv5rhl63h/images/target contains 8144 images
+/tmp/tmpv5rhl63h/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: 0.2153 - accuracy: 0.9278 - val_loss: 0.1581 - val_accuracy: 0.9464 - 47s/epoch - 142ms/step
+328/328 - 48s - loss: 0.2294 - accuracy: 0.9217 - val_loss: 0.1326 - val_accuracy: 0.9535 - 48s/epoch - 146ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0879 - accuracy: 0.9652 - val_loss: 0.2606 - val_accuracy: 0.9120 - 43s/epoch - 131ms/step
+328/328 - 44s - loss: 0.0975 - accuracy: 0.9639 - val_loss: 0.0903 - val_accuracy: 0.9641 - 44s/epoch - 134ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0638 - accuracy: 0.9756 - val_loss: 0.1235 - val_accuracy: 0.9596 - 43s/epoch - 131ms/step
+328/328 - 44s - loss: 0.0681 - accuracy: 0.9748 - val_loss: 0.1928 - val_accuracy: 0.9377 - 44s/epoch - 134ms/step
-<keras.callbacks.History object at 0x7f7af7237e50>
+<keras.callbacks.History object at 0x7f12803d7750>
</pre></div>
</div>
</div>
@@ -963,7 +963,7 @@ 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 43.647 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 58.815 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 d4de20985b..a5b8a7349e 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:57.822</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>08:20.689</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,30 +349,30 @@
</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>04:43.647</p></td>
+<td><p>05:58.815</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>01:09.962</p></td>
+<td><p>01:13.935</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>00:51.346</p></td>
+<td><p>00:54.606</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>00:09.005</p></td>
+<td><p>00:09.289</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>00:03.862</p></td>
+<td><p>00:04.043</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 d532b85e77..762b82039d 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.398</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:46.332</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.660</p></td>
+<td><p>00:34.197</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>00:10.221</p></td>
+<td><p>00:10.465</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>00:01.511</p></td>
+<td><p>00:01.665</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 8bbcd30a38..88e81c96b0 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f7bb32e08c0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f128002c8c0>
</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 132cc7d0da..4264fa5956 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.714</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.240</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.203</p></td>
+<td><p>00:05.681</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>00:01.154</p></td>
+<td><p>00:01.142</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.578</p></td>
+<td><p>00:00.602</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.559</p></td>
+<td><p>00:00.580</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>00:00.115</p></td>
+<td><p>00:00.121</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.050</p></td>
+<td><p>00:00.054</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.032</p></td>
+<td><p>00:00.033</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>00:00.026</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 52f44044d7..20278123e6 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -574,7 +574,7 @@ class Module:
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmptdv9y8gy/input0.cc'\nsource_filename = \"/tmp/tmptdv9y8gy/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmp3l6i0t5_/input0.cc'\nsource_filename = \"/tmp/tmp3l6i0t5_/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
</pre></div>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index f56141eb56..9063396749 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index fe6dbf6f3b..cbd28d44d0 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/6fdb1b7e3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 bd3f192223..d778eee258 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/6fdb1b7e3/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 384097a46f..6ca0aff4fb 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/6fdb1b7e3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 f381c52b84..93980802a2 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/6fdb1b7e3/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 2e9c052e29..ba790b7270 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/6fdb1b7e3/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 209f995443..84339fdf80 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/6fdb1b7e3/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 5b5ce92a41..2b9569c1e9 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/6fdb1b7e3/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 44c6518695..dd05f07427 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/6fdb1b7e3/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 b0fb6788b9..2492333646 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/6fdb1b7e3/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 a80f4a4845..7adbd2893a 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/6fdb1b7e3/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 c6504b864a..bef08fe715 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/6fdb1b7e3/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 fe54455121..64277068ac 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/6fdb1b7e3/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 00dfe2de6e..72696e44ad 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/6fdb1b7e3/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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/6fdb1b7e3/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fd3f8035c/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 262fb2b1f4..cc1e1818ba 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
... 1778 lines suppressed ...