You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/08/02 05:13:19 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@0261b8ed8b8b9c3df36964e6bbd785cfd7259b7d)
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 5029e6fa0 deploying docs (apache/tvm@0261b8ed8b8b9c3df36964e6bbd785cfd7259b7d)
5029e6fa0 is described below
commit 5029e6fa08ee707d00365a3f4b3a7763a2181174
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Aug 2 05:13:14 2022 +0000
deploying docs (apache/tvm@0261b8ed8b8b9c3df36964e6bbd785cfd7259b7d)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1690 +++++++++++---------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 114 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 2 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 40 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 16 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 23 +-
docs/how_to/deploy_models/deploy_prequantized.html | 15 +-
.../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 | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 18 +-
.../tune_conv2d_layer_cuda.html | 1686 ++++++++++---------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 114 +-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 2 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 40 +-
122 files changed, 2663 insertions(+), 2564 deletions(-)
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 020446d1f..8be795db1 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.767 seconds)
+ **Total running time of the script:** ( 1 minutes 6.390 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
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 6aaf6e90e..98a4531f7 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip39a44786-1d6d-4047-bfee-53dc12696a46 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe3ccce3b-6b09-489e-83bc-2f56d7679beb 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 3123a842e..06d3e5436 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:01, 31.8MB/s]
23%|##2 | 9.36M/41.5M [00:00<00:01, 20.9MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:01, 27.8MB/s]
42%|####1 | 17.3M/41.5M [00:00<00:00, 25.9MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.6MB/s]
62%|######1 | 25.6M/41.5M [00:00<00:00, 31.2MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 37.0MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 41.7MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 33.3MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:01, 36.1MB/s]
24%|##3 | 9.77M/41.5M [00:00<00:01, 23.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 30.6MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 36.3MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 46.8MB/s]
89%|########9 | 37.0M/41.5M [00:00<00:00, 45.9MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 39.9MB/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 6a58c09c3..c4a1b8a9f 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
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]
7%|6 | 3.05M/44.7M [00:00<00:01, 31.8MB/s]
14%|#3 | 6.08M/44.7M [00:00<00:01, 30.5MB/s]
69%|######9 | 30.9M/44.7M [00:00<00:00, 133MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 127MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
34%|###3 | 15.0M/44.7M [00:00<00:00, 157MB/s]
83%|########2 | 37.0M/44.7M [00:00<00:00, 200MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 200MB/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 e7f34be92..9ac379660 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.163 seconds)
+ **Total running time of the script:** ( 1 minutes 2.828 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 5a9820bd2..1d4d31f01 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:04.735** total execution time for **how_to_compile_models** files:
+**05:04.364** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:08.163 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:06.390 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:02.767 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.828 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.226 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.318 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.775 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.258 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.124 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.082 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.527 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.612 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.979 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.677 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.090 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.874 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.714 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.840 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.371 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.486 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 13ada8ccc..ed5d3c5f9 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
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9346 15.6007 16.6983 15.5188 0.4640
+ 15.6470 15.6370 15.7906 15.5861 0.0577
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 32a9a8ec8..64818d9b5 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
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
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]
2%|2 | 3.49M/170M [00:00<00:04, 36.5MB/s]
4%|4 | 6.97M/170M [00:00<00:04, 34.5MB/s]
13%|#2 | 21.8M/170M [00:00<00:01, 88.2MB/s]
26%|##5 | 43.8M/170M [00:00<00:00, 143MB/s]
40%|#### | 68.3M/170M [00:00<00:00, 184MB/s]
51%|#####1 | 87.4M/170M [00:00<00:00, 169MB/s]
62%|######2 | 106M/170M [00:00<00:00, 177MB/s]
73%|#######2 | 123M/170M [00:00<00:00, 130MB/s]
82%|########2 | 139M/170M [00:01<00:00, 139MB/s]
96%|#########6| 164M/170M [00:01<00:00, 169MB/s]
100%|##########| 170M/170M [00:01<00:00, 149MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
7%|7 | 12.1M/170M [00:00<00:01, 127MB/s]
18%|#8 | 31.0M/170M [00:00<00:00, 168MB/s]
29%|##9 | 49.4M/170M [00:00<00:00, 180MB/s]
40%|#### | 68.5M/170M [00:00<00:00, 188MB/s]
51%|##### | 86.4M/170M [00:00<00:00, 188MB/s]
62%|######2 | 105M/170M [00:00<00:00, 191MB/s]
73%|#######3 | 124M/170M [00:00<00:00, 193MB/s]
84%|########3 | 143M/170M [00:00<00:00, 183MB/s]
94%|#########4| 160M/170M [00:00<00:00, 154MB/s]
100%|##########| 170M/170M [00:01<00:00, 170MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: 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)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: 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').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 55.931 seconds)
+ **Total running time of the script:** ( 3 minutes 1.108 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 c68ed9c59..04871b5dd 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
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]
37%|###6 | 5.01M/13.6M [00:00<00:00, 51.7MB/s]
73%|#######3 | 9.95M/13.6M [00:00<00:00, 38.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 36.6MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
10%|9 | 1.31M/13.6M [00:00<00:00, 13.7MB/s]
19%|#9 | 2.62M/13.6M [00:00<00:00, 13.4MB/s]
30%|### | 4.12M/13.6M [00:00<00:00, 14.2MB/s]
40%|#### | 5.48M/13.6M [00:00<00:01, 7.56MB/s]
55%|#####4 | 7.43M/13.6M [00:00<00:00, 10.5MB/s]
70%|######9 | 9.43M/13.6M [00:00<00:00, 13.0MB/s]
85%|########4 | 11.5M/13.6M [00:00<00:00, 15.3MB/s]
100%|##########| 13.6M/13.6M [00:01<00:00, 13.9MB/s]
@@ -412,7 +412,7 @@ 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)
- 90.2164 90.1745 92.2312 90.0624 0.2367
+ 90.2356 90.1851 91.9263 89.9990 0.2205
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.223 seconds)
+ **Total running time of the script:** ( 1 minutes 10.549 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 6f4f4c2cd..aec842181 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
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.4009 119.3560 120.4940 118.4916 0.3963
+ 120.1575 120.1845 121.8541 118.7708 0.7848
@@ -476,7 +476,7 @@ 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:** ( 1 minutes 51.112 seconds)
+ **Total running time of the script:** ( 1 minutes 52.855 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 f98b9a4e2..2a3a1e6a8 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.956 seconds)
+ **Total running time of the script:** ( 1 minutes 34.488 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 41e383727..790487872 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
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3600/132723 [00:00<00:03, 35997.72KB/s]
7%|7 | 9901/132723 [00:00<00:02, 51881.60KB/s]
14%|#4 | 18858/132723 [00:00<00:01, 69086.81KB/s]
21%|## | 27773/132723 [00:00<00:01, 77001.52KB/s]
27%|##6 | 35474/132723 [00:00<00:01, 76495.81KB/s]
33%|###3 | 44416/132723 [00:00<00:01, 80868.71KB/s]
40%|###9 | 52506/132723 [00:00<00:01, 50135.47KB/s]
46%|####6 | 61425/132723 [00:00<00:01, 58881.10KB/s]
52%|#####1 | 68601/132723 [00:01<00:01, 61518.90KB/s]
58%|#####8 | 77573/132723 [00:01<00:00, 68727.57KB/s]
64%|######4 | 85255/132723 [00:01<00:00, 55557.75KB/s]
71%|####### | 94079/132723 [00:01<00:00, 63089.49KB/s]
76%|#######6 | 101278/132723 [00:01<00:00, 44383.40KB/s]
82%|########2 | 109483/132723 [00:01<00:00, 51685.83KB/s]
87%|########7 | 115988/132723 [00:02<00:00, 22130.75KB/s]
93%|#########
2| 122993/132723 [00:02<00:00, 27478.72KB/s]
99%|#########9| 131781/132723 [00:02<00:00, 35784.70KB/s]
100%|##########| 132723/132723 [00:02<00:00, 46094.31KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6805/132723 [00:00<00:01, 68040.49KB/s]
11%|#1 | 14983/132723 [00:00<00:01, 76116.37KB/s]
17%|#7 | 22595/132723 [00:00<00:03, 35265.90KB/s]
23%|##3 | 30568/132723 [00:00<00:02, 45583.70KB/s]
28%|##7 | 36814/132723 [00:00<00:02, 40570.75KB/s]
34%|###3 | 44743/132723 [00:00<00:01, 49271.05KB/s]
38%|###8 | 50852/132723 [00:01<00:02, 40437.16KB/s]
44%|####4 | 58897/132723 [00:01<00:01, 48923.26KB/s]
50%|##### | 66979/132723 [00:01<00:01, 56339.05KB/s]
57%|#####6 | 75078/132723 [00:01<00:00, 62484.43KB/s]
62%|######1 | 82169/132723 [00:01<00:00, 58183.13KB/s]
68%|######7 | 90026/132723 [00:01<00:00, 63324.96KB/s]
74%|#######4 | 98257/132723 [00:01<00:00, 68350.53KB/s]
80%|#######9 | 105541/132723 [00:02<00:00, 54592.59KB/s]
86%|########5 | 113503/132723 [00:02<00:00, 60480.75KB/s]
91%|#########
| 120223/132723 [00:02<00:00, 44721.80KB/s]
97%|#########6| 128217/132723 [00:02<00:00, 51955.12KB/s]
100%|##########| 132723/132723 [00:02<00:00, 52704.65KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 32.917 seconds)
+ **Total running time of the script:** ( 2 minutes 30.151 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 20e70dd88..5439fa6c2 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:20.224** total execution time for **how_to_deploy_models** files:
+**11:22.417** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:55.931 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:01.108 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:32.917 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:30.151 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:51.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:52.855 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:36.956 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:34.488 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:09.223 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.549 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.225 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.059 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.068 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.260 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.786 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.941 | 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 025e0f328..a4e1f9227 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
@@ -476,7 +476,7 @@ 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.zipd1a0b406-e3d9-445f-a0d5-6bdf695a672d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip1349ce1a-fcce-4761-8b07-02c10642bb9c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -590,7 +590,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
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 d3bae6446..c5d5fc5b5 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
=================
-**00:40.403** total execution time for **how_to_extend_tvm** files:
+**00:39.412** 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``) | 00:37.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:36.293 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.225 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.157 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.929 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.949 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.013 | 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 b30cbc427..893349c03 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6538us [6538us] (46.06%; 46.06%)
- FoldScaleAxis: 7657us [6us] (53.94%; 53.94%)
- FoldConstant: 7651us [1576us] (53.90%; 99.93%)
- InferType: 6075us [6075us] (42.80%; 79.40%)
+ InferType: 6542us [6542us] (45.59%; 45.59%)
+ FoldScaleAxis: 7806us [6us] (54.41%; 54.41%)
+ FoldConstant: 7801us [1602us] (54.37%; 99.93%)
+ InferType: 6199us [6199us] (43.21%; 79.47%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6119us [6119us] (44.41%; 44.41%)
- FoldScaleAxis: 7658us [5us] (55.59%; 55.59%)
- FoldConstant: 7653us [1583us] (55.55%; 99.94%)
- InferType: 6071us [6071us] (44.06%; 79.32%)
+ InferType: 6213us [6213us] (44.61%; 44.61%)
+ FoldScaleAxis: 7714us [5us] (55.39%; 55.39%)
+ FoldConstant: 7709us [1595us] (55.36%; 99.94%)
+ InferType: 6114us [6114us] (43.90%; 79.31%)
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 b27f8b7e9..356bdd77c 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 33.071917 ms
+ Convolution: 54.204385 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 e75effb36..cf6a0219f 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
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 8.248792 ms
+ conv2d with tensor core: 8.873218 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 7770a724a..b8708ced1 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018744
- Baseline: 3.400800
+ Numpy running time: 0.018482
+ Baseline: 3.322170
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.304235
+ Opt1: 0.304844
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335194
+ Opt2: 0.344033
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118273
+ Opt3: 0.112513
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111086
+ Opt4: 0.108665
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111779
+ Opt5: 0.110813
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145234
+ Opt6: 0.144883
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 214898839..a730fa50b 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
=================
-**00:34.493** total execution time for **how_to_optimize_operators** files:
+**00:34.249** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.300 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.047 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.221 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.224 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.971 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.978 | 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 d51d41000..0dad5653b 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
=================
-**05:58.573** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:18.797** 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``) | 03:15.612 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:27.004 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.830 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.086 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.346 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.292 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.245 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.302 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.799 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.632 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.741 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.481 | 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 60c96069b..184db0475 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
@@ -206,6 +206,13 @@ file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+
+ .T
+
@@ -240,422 +247,483 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[16] = 0f32
- conv2d_nchw_1[20] = 0f32
- conv2d_nchw_1[24] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[13] = 0f32
- conv2d_nchw_1[17] = 0f32
- conv2d_nchw_1[21] = 0f32
- conv2d_nchw_1[25] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[18] = 0f32
- conv2d_nchw_1[22] = 0f32
- conv2d_nchw_1[26] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[15] = 0f32
- conv2d_nchw_1[19] = 0f32
- conv2d_nchw_1[23] = 0f32
- conv2d_nchw_1[27] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[(threadIdx.x_1*18)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 1)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 2)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 3)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 4)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 5)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 6)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 7)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 8)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 9)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 10)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 11)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 12)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 13)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 14)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 15)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 16)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 17)] = 0f32
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3)) + 142848)]
- }
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -710,7 +778,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.316 ms
+ Execution time of this operator: 0.361 ms
@@ -759,36 +827,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_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=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -807,12 +875,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=18)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -832,376 +900,430 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[2304];
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
- conv2d_nchw[26] = 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[15] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
- conv2d_nchw[27] = 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) {
- __syncthreads();
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[(((int)threadIdx.x) * 18)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 142848)];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ 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 i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -1263,7 +1385,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 15.612 seconds)
+ **Total running time of the script:** ( 3 minutes 27.004 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 9b45c6658..2f61b92cb 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)
- 9.8218 9.8302 9.8654 9.7698 0.0395
+ 9.9402 9.9441 9.9738 9.9027 0.0292
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 31dba528b..07a27735f 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)
- 760.6107 761.1158 762.3256 758.3907 1.6456
+ 749.8601 749.8542 751.2388 748.4872 1.1233
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.830 seconds)
+ **Total running time of the script:** ( 1 minutes 21.086 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 147aede88..0f0eec3f0 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
@@ -397,106 +397,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = ((i.outer.inner*64) + (i.inner*16))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*64) + (i.inner*16)) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*64) + (i.inner*16)) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*64) + (i.inner*16)) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*64) + (i.inner*16)) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*64) + (i.inner*16)) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*64) + (i.inner*16)) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*64) + (i.inner*16)) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*64) + (i.inner*16)) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*64) + (i.inner*16)) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*64) + (i.inner*16)) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*64) + (i.inner*16)) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*64) + (i.inner*16)) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*64) + (i.inner*16)) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = (((i.outer.inner*64) + (i.inner*16)) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = (((i.outer.inner*64) + (i.inner*16)) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -552,7 +476,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.124 ms
+ Execution time of this operator: 1.543 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 140b2dc58..60f3f0264 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:45.294** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.504** 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``) | 00:45.259 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.468 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
++--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index a7320f4f8..98e907213 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
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('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, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 80.69/80.69 result: MeasureResult(costs=(0.002868899028571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8650996685028076, timestamp=1659410039.641088) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/80.69 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 218.51/218.51 result: MeasureResult(costs=(0.001059437227586207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1403276920318604, timestamp=1659411506.1598961) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/218.51 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.46/260.46 result: MeasureResult(costs=(0.0008888055027624309,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7665715217590332, timestamp=1659410040.5633569) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.24/260.24 result: MeasureResult(costs=(0.0008895562265193371,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7725238800048828, timestamp=1659411507.0843732) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.30/260.46 result: MeasureResult(costs=(0.0436386055,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8647127151489258, timestamp=1659410045.122671) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.35/260.46 result: MeasureResult(costs=(0.0691087085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.52761435508728, timestamp=1659410046.358635) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.25/260.24 result: MeasureResult(costs=(0.04406296375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8488798141479492, timestamp=1659411511.6304812) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/260.24 result: MeasureResult(costs=(0.0694109735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.502104997634888, timestamp=1659411512.8628416) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.00/260.46 result: MeasureResult(costs=(0.008266975642857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2550444602966309, timestamp=1659410057.4064996) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.08/260.24 result: MeasureResult(costs=(0.008245470285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3395006656646729, timestamp=1659411523.9112604) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001296
+ Time cost of this operator: 0.001244
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 55e63fa8a..3bc8b79a5 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.727 (1, 2, 10, 10, 3) 2 1 [310.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.045 0.969 (1, 6, 10, 10) 1 1 [3.045]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.304 (1, 1, 10, 10, 3) 1 1 [0.957]
- Total_time - 314.302 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.2 98.731 (1, 2, 10, 10, 3) 2 1 [313.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.071 0.968 (1, 6, 10, 10) 1 1 [3.071]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.301 (1, 1, 10, 10, 3) 1 1 [0.955]
+ Total_time - 317.226 - - - - -
@@ -398,10 +398,10 @@ 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 79.375 96.606 (1, 6, 10, 10, 1) 2 1 [79.375]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.823 2.219 (1, 6, 10, 10) 1 1 [1.823]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 1.174 (1, 1, 10, 10, 3) 1 1 [0.965]
- Total_time - 82.163 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.375 96.637 (1, 6, 10, 10, 1) 2 1 [79.375]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.798 2.188 (1, 6, 10, 10) 1 1 [1.798]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 1.175 (1, 1, 10, 10, 3) 1 1 [0.965]
+ Total_time - 82.138 - - - - -
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 49b4b734a..7487a293b 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpwigspvrk/images/random'
+ '/tmp/tmps44wm1mc/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpwigspvrk/images/target contains 8144 images
- /tmp/tmpwigspvrk/images/random contains 5000 images
+ /tmp/tmps44wm1mc/images/target contains 8144 images
+ /tmp/tmps44wm1mc/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2141 - accuracy: 0.9277 - val_loss: 0.1536 - val_accuracy: 0.9547
+ 328/328 - 55s - loss: 0.2099 - accuracy: 0.9278 - val_loss: 0.1353 - val_accuracy: 0.9573
Epoch 2/3
- 328/328 - 52s - loss: 0.1017 - accuracy: 0.9622 - val_loss: 0.1156 - val_accuracy: 0.9653
+ 328/328 - 52s - loss: 0.0958 - accuracy: 0.9649 - val_loss: 0.1169 - val_accuracy: 0.9687
Epoch 3/3
- 328/328 - 52s - loss: 0.0657 - accuracy: 0.9754 - val_loss: 0.1009 - val_accuracy: 0.9698
+ 328/328 - 56s - loss: 0.0674 - accuracy: 0.9757 - val_loss: 0.1150 - val_accuracy: 0.9649
- <keras.callbacks.History object at 0x7f1efa831950>
+ <keras.callbacks.History object at 0x7fc9f44670d0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 17.887 seconds)
+ **Total running time of the script:** ( 4 minutes 47.210 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 ab8f227e4..8b945abb3 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:11.301** total execution time for **how_to_work_with_microtvm** files:
+**05:38.758** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:17.887 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:47.210 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.107 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.025 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.962 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.220 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.343 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.302 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 501f4f8ff..c334c9c4b 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
=================
-**00:42.224** total execution time for **how_to_work_with_relay** files:
+**00:41.307** 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``) | 00:30.836 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.129 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.829 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.685 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.552 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.485 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 1d19c507e..9d6e2b9e6 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f1e64208c20>
+ <function my_cuda_math_rule at 0x7fc9f58a3560>
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 132a94ba4..fa535db36 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.074** total execution time for **how_to_work_with_schedules** files:
+**00:03.958** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.893 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.855 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.951 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.884 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.532 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.522 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.517 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.508 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.107 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 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 df8f5817b..39eea3fc6 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpq2xm5tv_/input0.cc'\nsource_filename = \"/tmp/tmpq2xm5tv_/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpi38qfaam/input0.cc'\nsource_filename = \"/tmp/tmpi38qfaam/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 7e27a29a3..15ca88c3d 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
=================
-**00:21.245** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.023** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.239 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.017 | 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 ccd96766c..b24807ee3 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ 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 23.13s!
+ resnet18_v1 inference graph built in 22.67s!
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 83ba861e0..086e4c818 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.02s!
+ yolov3-tiny inference graph built in 16.09s!
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 739366beb..cbd519b39 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
=================
-**01:32.541** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.445** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.230 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.666 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.311 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.778 | 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 cd47896e6..18578556e 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
=================
-**00:03.204** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.252** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.806 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.868 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.399 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.385 | 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 132ce3416..78fd069d3 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
=================
-**00:00.714** total execution time for **topic_vta_tutorials** files:
+**00:00.694** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.382 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.370 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.332 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.324 | 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 06ead0ffa..12b02476b 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.551 ms
+ Execution time of this operator: 93.898 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index e8e8156bd..a4414eacd 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.61/10.61 result: MeasureResult(costs=(0.025294538999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5397012233734131, timestamp=1659408838.7096004) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.93/10.61 result: MeasureResult(costs=(0.0915333492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6175546646118164, timestamp=1659408840.3378012) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022695635999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6015610694885254, timestamp=1659408841.3872285) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.42/11.83 result: MeasureResult(costs=(0.1894552552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1577374935150146, timestamp=1659408845.1159136) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.54/11.83 result: MeasureResult(costs=(0.07583382860000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3500444889068604, timestamp=1659408846.5962448) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.54/11.83 result: MeasureResult(costs=(0.1742443344,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.945324182510376, timestamp=1659408849.5857105) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.84/11.83 result: MeasureResult(costs=(0.32029403320000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.24799919128418, timestamp=1659408855.3940082) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.19/11.83 result: MeasureResult(costs=(0.026343662,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5618143081665039, timestamp=1659408855.9780061) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.56/11.83 result: MeasureResult(costs=(0.172617332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.867321729660034, timestamp=1659408858.9649155) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.49/11.83 result: MeasureResult(costs=(0.1077967698,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8286898136138916, timestamp=1659408860.8513565) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.56/10.56 result: MeasureResult(costs=(0.025424939,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.544111967086792, timestamp=1659410295.3199446) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.94/10.56 result: MeasureResult(costs=(0.09141061539999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6080753803253174, timestamp=1659410297.4769225) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.022680726999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5954163074493408, timestamp=1659410298.046174) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.85/11.84 result: MeasureResult(costs=(0.1454228474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4518978595733643, timestamp=1659410301.0675182) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.66/11.84 result: MeasureResult(costs=(0.0733388552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3104808330535889, timestamp=1659410302.5029118) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.79/11.84 result: MeasureResult(costs=(0.149961646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.52341628074646, timestamp=1659410305.5947134) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.84 result: MeasureResult(costs=(0.307517514,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.038498878479004, timestamp=1659410310.6786737) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.64/11.84 result: MeasureResult(costs=(0.025228234999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5508103370666504, timestamp=1659410311.245852) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.90/11.84 result: MeasureResult(costs=(0.141155082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3602657318115234, timestamp=1659410313.7249591) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.78/11.84 result: MeasureResult(costs=(0.0966290474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.652329683303833, timestamp=1659410315.4350224) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index cdc31c12c..02b74157a 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 494.0234241400003, 'median': 493.8491089500019, 'std': 1.1897826468649766}
+ {'mean': 495.3543460900017, 'median': 495.1141643500023, 'std': 1.0669017038663995}
@@ -563,30 +563,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (4/20) | 6.30 s
[Task 1/25] Current/Best: 6.15/ 17.49 GFLOPS | Progress: (8/20) | 9.22 s
[Task 1/25] Current/Best: 11.55/ 22.78 GFLOPS | Progress: (12/20) | 11.64 s
[Task 1/25] Current/Best: 16.87/ 22.80 GFLOPS | Progress: (16/20) | 13.33 s
[Task 1/25] Current/Best: 11.59/ 23.94 GFLOPS | Progress: (20/20) | 15.05 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.29/ 13.00 GFLOPS | Progress: (4/20) | 3.77 s
[Task 2/25] Current/Best: 14.09/ 18.91 GFLOPS | Progress: (8/20) | 5.09 s
[Task 2/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (12/20) | 6.41 s
[Task 2/25] Current/Best: 12.44/ 20.59 GFLOPS | Progress: (16/20) | 7.69 s
[Task 2/25] Current/Best: 19.49/ 20.59 GFLOPS | Progress: (20/20) | 9.23 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.60 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.59/ 16.83 GFLOPS | Progress: (8/20) | 7.76 s
[Task 3/25] Current/Best: 14.92/ 16.83 GFLOPS | Progress: (12/20) | 9.48 s
[Task 3/25] Current/Best: 7.22/ 23.82 GFLOPS | Progress: (16/20) | 11.38 s
[Task 3/25] Current/Best: 12.65/ 23.82 GFLOPS | Progress: (20/20) | 15.90 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.50 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.42/ 20.50 GFLOPS | Progress: (8/20) | 6.71 s
[Task 4/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (12/20) | 11.29 s
[Task 4/25] Current/Best: 16.64/ 22.19 GFLOPS | Progress: (16/20) | 13.49 s
[Task 4/25] Current/Best: 12.87/ 22.19 GFLOPS | Progress: (20/20) | 15.49 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.70/ 10.30 GFLOPS | Progress: (4/20) | 2.60 s
[Task 5/25] Current/Best: 11.68/ 11.68 GFLOPS | Progress: (8/20) | 4.66 s
[Task 5/25] Current/Best: 11.68/ 18.06 GFLOPS | Progress: (12/20) | 7.76 s
[Task 5/25] Current/Best: 11.82/ 22.72 GFLOPS | Progress: (16/20) | 9.17 s
[Task 5/25] Current/Best: 12.01/ 22.72 GFLOPS | Progress: (20/20) | 11.03 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.11/ 20.73 GFLOPS | Progress: (4/20) | 3.97 s
[Task 6/25] Current/Best: 19.00/ 20.73 GFLOPS | Progress: (8/20) | 5.74 s
[Task 6/25] Current/Best: 13.27/ 20.73 GFLOPS | Progress: (12/20) | 7.67 s
[Task 6/25] Current/Best: 19.92/ 20.73 GFLOPS | Progress: (16/20) | 9.90 s
[Task 6/25] Current/Best: 3.76/ 20.73 GFLOPS | Progress: (20/20) | 12.41 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.01/ 13.01 GFLOPS | Progress: (4/20) | 3.57 s
[Task 7/25] Current/Best: 20.33/ 21.16 GFLOPS | Progress: (8/20) | 5.09 s
[Task 7/25] Current/Best: 16.08/ 21.16 GFLOPS | Progress: (12/20) | 7.02 s
[Task 7/25] Current/Best: 12.26/ 21.16 GFLOPS | Progress: (16/20) | 9.06 s
[Task 7/25] Current/Best: 6.38/ 21.76 GFLOPS | Progress: (20/20) | 11.52 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.69/ 13.67 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.35/ 13.67 GFLOPS | Progress: (8/20) | 7.59 s
[Task 8/25] Current/Best: 12.50/ 13.67 GFLOPS | Progress: (12/20) | 13.65 s
[Task 8/25] Current/Best: 18.77/ 18.77 GFLOPS | Progress: (16/20) | 15.76 s
[Task 8/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (20/20) | 22.28 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.35/ 15.93 GFLOPS | Progress: (4/20) | 11.95 s
[Task 9/25] Current/Best: 23.61/ 23.61 GFLOPS | Progress: (8/20) | 13.77 s
[Task 9/25] Current/Best: 8.28/ 23.61 GFLOPS | Progress: (12/20) | 16.16 s
[Task 9/25] Current/Best: 17.98/ 23.61 GFLOPS | Progress: (16/20) | 18.72 s
[Task 9/25] Current/Best: 9.00/ 23.61 GFLOPS | Progress: (20/20) | 26.32 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 2.60 s
[Task 10/25] Current/Best: 15.47/ 18.15 GFLOPS | Progress: (8/20) | 4.17 s
[Task 10/25] Current/Best: 12.43/ 19.02 GFLOPS | Progress: (12/20) | 5.70 s
[Task 10/25] Current/Best: 18.77/ 20.28 GFLOPS | Progress: (16/20) | 6.81 s
[Task 10/25] Current/Best: 8.87/ 20.28 GFLOPS | Progress: (20/20
) | 8.37 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.79/ 18.17 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.86/ 18.17 GFLOPS | Progress: (8/20) | 6.04 s
[Task 11/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (12/20) | 8.08 s
[Task 11/25] Current/Best: 13.47/ 21.14 GFLOPS | Progress: (16/20) | 10.83 s
[Task 11/25] Current/Best: 19.45/ 21.54 GFLOPS | Progress: (20/20) | 12.88 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 17.94 GFLOPS | Progress: (4/20) | 5.44 s
[Task 12/25] Current/Best: 5.21/ 17.94 GFLOPS | Progress: (8/20) | 9.15 s
[Task 12/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (12/20) | 11.16 s
[Task 12/25] Current/Best: 15.27/ 18.81 GFLOPS | Progress: (16/20) | 13.94 s
[Task 12/25] Current/Best: 15.15/ 18.86 GFLOPS | Progress: (20/20) | 15.86 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.74/ 17.32 GFLOPS | Progress: (4/20) | 3.73 s
[Task 13/25] Current/Best: 16.04/ 20.75 GFLOPS | Progress: (8/20) | 6.17 s
[Task 13/25] Current/Best: 19.44/ 21.50 GFLOPS | Progress: (12/20) | 9.12 s
[Task 13/25] Current/Best: 12.21/ 21.50 GFLOPS | Progress: (16/20) | 12.55 s
[Task 13/25] Current/Best: 18.76/ 21.50 GFLOPS | Progress: (20/20) | 14.81 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.60/ 13.60 GFLOPS | Progress: (4/20) | 3.39 s
[Task 14/25] Current/Best: 5.97/ 13.60 GFLOPS | Progress: (8/20) | 5.59 s
[Task 14/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (12/20) | 8.16 s
[Task 14/25] Current/Best: 15.53/ 20.34 GFLOPS | Progress: (16/20) | 9.82 s Done.
-
[Task 14/25] Current/Best: 17.18/ 20.34 GFLOPS | Progress: (20/20) | 11.55 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.14/ 17.65 GFLOPS | Progress: (4/20) | 2.73 s
[Task 15/25] Current/Best: 13.87/ 18.10 GFLOPS | Progress: (8/20) | 4.06 s
[Task 15/25] Current/Best: 10.41/ 22.22 GFLOPS | Progress: (12/20) | 6.14 s
[Task 15/25] Current/Best: 20.39/ 22.22 GFLOPS | Progress: (16/20) | 9.11 s
[Task 15/25] Current/Best: 9.72/ 22.22 GFLOPS | Progress: (20/20) | 10.08 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.87/ 20.87 GFLOPS | Progress: (4/20) | 2.95 s
[Task 16/25] Current/Best: 3.03/ 20.87 GFLOPS | Progress: (8/20) | 4.57 s
[Task 16/25] Current/Best: 19.55/ 20.87 GFLOPS | Progress: (12/20) | 5.78 s
[Task 16/25] Current/Best: 18.56/ 20.87 GFLOPS | Progress: (16/20) |
7.12 s
[Task 16/25] Current/Best: 10.01/ 21.97 GFLOPS | Progress: (20/20) | 9.17 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.26/ 18.85 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.37/ 23.26 GFLOPS | Progress: (8/20) | 7.59 s
[Task 17/25] Current/Best: 16.77/ 23.26 GFLOPS | Progress: (12/20) | 9.66 s
[Task 17/25] Current/Best: 16.52/ 23.26 GFLOPS | Progress: (16/20) | 11.82 s
[Task 17/25] Current/Best: 10.03/ 23.26 GFLOPS | Progress: (20/20) | 13.94 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.21/ 18.19 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 10.57/ 19.87 GFLOPS | Progress: (8/20) | 7.14 s
[Task 18/25] Current/Best: 19.24/ 19.87 GFLOPS | Progress: (12/20) | 9.06 s
[Task 18/25] Current/Best: 10.08/ 19.87 GFLOPS | Progress: (16/20) | 12.68 s
[Task 18/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (20/20) | 14.20 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.05/ 20.16 GFLOPS | Progress: (4/20) | 6.19 s
[Task 19/25] Current/Best: 2.61/ 20.16 GFLOPS | Progress: (8/20) | 9.47 s
[Task 19/25] Current/Best: 17.88/ 20.91 GFLOPS | Progress: (12/20) | 12.31 s
[Task 19/25] Current/Best: 15.37/ 21.17 GFLOPS | Progress: (16/20) | 15.19 s
[Task 19/25] Current/Best: 2.70/ 22.81 GFLOPS | Progress: (20/20) | 17.98 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.78/ 14.91 GFLOPS | Progress: (4/20) | 3.40 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.46/ 17.46 GFLOPS | Progress: (4/20) | 6.21 s
[Task 1/25] Current/Best: 6.16/ 17.46 GFLOPS | Progress: (8/20) | 9.23 s
[Task 1/25] Current/Best: 11.55/ 22.77 GFLOPS | Progress: (12/20) | 11.65 s
[Task 1/25] Current/Best: 16.88/ 22.85 GFLOPS | Progress: (16/20) | 13.32 s
[Task 1/25] Current/Best: 11.59/ 23.92 GFLOPS | Progress: (20/20) | 15.09 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.22/ 13.09 GFLOPS | Progress: (4/20) | 3.75 s
[Task 2/25] Current/Best: 14.30/ 18.64 GFLOPS | Progress: (8/20) | 5.05 s
[Task 2/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (12/20) | 6.40 s
[Task 2/25] Current/Best: 12.11/ 21.17 GFLOPS | Progress: (16/20) | 7.65 s
[Task 2/25] Current/Best: 18.72/ 21.17 GFLOPS | Progress: (20/20) | 9.25 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.59 GFLOPS | Progress: (4/20) | 5.84 s
[Task 3/25] Current/Best: 15.60/ 16.89 GFLOPS | Progress: (8/20) | 7.75 s
[Task 3/25] Current/Best: 14.91/ 16.89 GFLOPS | Progress: (12/20) | 9.48 s
[Task 3/25] Current/Best: 7.19/ 23.83 GFLOPS | Progress: (16/20) | 11.41 s
[Task 3/25] Current/Best: 12.63/ 23.83 GFLOPS | Progress: (20/20) | 15.90 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.41 GFLOPS | Progress: (4/20) | 2.37 s
[Task 4/25] Current/Best: 6.84/ 20.41 GFLOPS | Progress: (8/20) | 6.69 s
[Task 4/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (12/20) | 11.19 s
[Task 4/25] Current/Best: 17.37/ 22.56 GFLOPS | Progress: (16/20) | 13.42 s
[Task 4/25] Current/Best: 13.29/ 22.56 GFLOPS | Progress: (20/20) | 15.44 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.71/ 10.10 GFLOPS | Progress: (4/20) | 2.60 s
[Task 5/25] Current/Best: 11.71/ 12.61 GFLOPS | Progress: (8/20) | 4.67 s
[Task 5/25] Current/Best: 11.67/ 18.12 GFLOPS | Progress: (12/20) | 7.73 s
[Task 5/25] Current/Best: 11.77/ 22.66 GFLOPS | Progress: (16/20) | 9.15 s
[Task 5/25] Current/Best: 12.11/ 22.66 GFLOPS | Progress: (20/20) | 11.01 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.12/ 20.69 GFLOPS | Progress: (4/20) | 3.97 s
[Task 6/25] Current/Best: 19.04/ 20.69 GFLOPS | Progress: (8/20) | 5.72 s
[Task 6/25] Current/Best: 13.34/ 20.69 GFLOPS | Progress: (12/20) | 7.64 s
[Task 6/25] Current/Best: 20.03/ 20.69 GFLOPS | Progress: (16/20) | 9.86 s
[Task 6/25] Current/Best: 3.73/ 20.69 GFLOPS | Progress: (20/20) | 12.41 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.17/ 12.85 GFLOPS | Progress: (4/20) | 3.61 s
[Task 7/25] Current/Best: 20.14/ 21.18 GFLOPS | Progress: (8/20) | 5.12 s
[Task 7/25] Current/Best: 14.39/ 21.18 GFLOPS | Progress: (12/20) | 7.05 s
[Task 7/25] Current/Best: 12.25/ 21.18 GFLOPS | Progress: (16/20) | 9.10 s
[Task 7/25] Current/Best: 6.32/ 21.83 GFLOPS | Progress: (20/20) | 11.54 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.86/ 13.65 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.56/ 13.65 GFLOPS | Progress: (8/20) | 7.68 s
[Task 8/25] Current/Best: 12.57/ 13.65 GFLOPS | Progress: (12/20) | 13.78 s
[Task 8/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (16/20) | 15.88 s
[Task 8/25] Current/Best: 19.49/ 19.49 GFLOPS | Progress: (20/20) | 22.36 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.34/ 15.76 GFLOPS | Progress: (4/20) | 11.95 s
[Task 9/25] Current/Best: 23.19/ 23.19 GFLOPS | Progress: (8/20) | 13.77 s
[Task 9/25] Current/Best: 8.24/ 23.19 GFLOPS | Progress: (12/20) | 16.13 s
[Task 9/25] Current/Best: 17.90/ 23.19 GFLOPS | Progress: (16/20) | 18.69 s
[Task 9/25] Current/Best: 9.20/ 23.19 GFLOPS | Progress: (20/20) | 26.44 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.34/ 18.34 GFLOPS | Progress: (4/20) | 2.58 s
[Task 10/25] Current/Best: 15.52/ 18.34 GFLOPS | Progress: (8/20) | 4.16 s
[Task 10/25] Current/Best: 12.63/ 18.85 GFLOPS | Progress: (12/20) | 5.69 s
[Task 10/25] Current/Best: 19.21/ 20.34 GFLOPS | Progress: (16/20) | 6.79 s
[Task 10/25] Current/Best: 8.88/ 20.34 GFLOPS | Progress: (20/20
) | 8.31 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.81/ 18.22 GFLOPS | Progress: (4/20) | 3.30 s
[Task 11/25] Current/Best: 16.75/ 18.22 GFLOPS | Progress: (8/20) | 6.02 s
[Task 11/25] Current/Best: 16.58/ 18.22 GFLOPS | Progress: (12/20) | 8.10 s
[Task 11/25] Current/Best: 13.37/ 21.19 GFLOPS | Progress: (16/20) | 10.87 s
[Task 11/25] Current/Best: 19.42/ 21.54 GFLOPS | Progress: (20/20) | 12.90 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.84/ 18.02 GFLOPS | Progress: (4/20) | 5.38 s
[Task 12/25] Current/Best: 5.24/ 18.02 GFLOPS | Progress: (8/20) | 9.10 s
[Task 12/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (12/20) | 11.08 s
[Task 12/25] Current/Best: 15.22/ 18.86 GFLOPS | Progress: (16/20) | 13.89 s
[Task 12/25] Current/Best: 15.08/ 18.86 GFLOPS | Progress: (20/20) | 15.81 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.02/ 17.27 GFLOPS | Progress: (4/20) | 3.67 s
[Task 13/25] Current/Best: 16.04/ 20.90 GFLOPS | Progress: (8/20) | 6.13 s
[Task 13/25] Current/Best: 19.60/ 21.70 GFLOPS | Progress: (12/20) | 9.00 s
[Task 13/25] Current/Best: 12.32/ 21.70 GFLOPS | Progress: (16/20) | 12.42 s
[Task 13/25] Current/Best: 18.51/ 21.70 GFLOPS | Progress: (20/20) | 14.67 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.61/ 13.61 GFLOPS | Progress: (4/20) | 3.33 s
[Task 14/25] Current/Best: 6.13/ 13.61 GFLOPS | Progress: (8/20) | 5.51 s
[Task 14/25] Current/Best: 19.57/ 19.57 GFLOPS | Progress: (12/20) | 8.05 s
[Task 14/25] Current/Best: 16.09/ 19.57 GFLOPS | Progress: (16/20) | 9.70 s Done.
+
[Task 14/25] Current/Best: 17.32/ 19.57 GFLOPS | Progress: (20/20) | 11.43 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.15/ 17.60 GFLOPS | Progress: (4/20) | 2.69 s
[Task 15/25] Current/Best: 14.49/ 18.10 GFLOPS | Progress: (8/20) | 4.02 s
[Task 15/25] Current/Best: 10.37/ 22.23 GFLOPS | Progress: (12/20) | 6.06 s
[Task 15/25] Current/Best: 20.44/ 22.23 GFLOPS | Progress: (16/20) | 8.99 s
[Task 15/25] Current/Best: 9.69/ 22.23 GFLOPS | Progress: (20/20) | 9.96 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.24/ 20.24 GFLOPS | Progress: (4/20) | 2.94 s
[Task 16/25] Current/Best: 3.04/ 20.24 GFLOPS | Progress: (8/20) | 4.56 s
[Task 16/25] Current/Best: 19.57/ 20.24 GFLOPS | Progress: (12/20) | 5.78 s
[Task 16/25] Current/Best: 17.54/ 20.24 GFLOPS | Progress: (16/20) |
7.14 s
[Task 16/25] Current/Best: 10.05/ 22.18 GFLOPS | Progress: (20/20) | 9.20 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.16/ 18.75 GFLOPS | Progress: (4/20) | 4.71 s
[Task 17/25] Current/Best: 14.35/ 23.39 GFLOPS | Progress: (8/20) | 7.45 s
[Task 17/25] Current/Best: 16.91/ 23.39 GFLOPS | Progress: (12/20) | 9.50 s
[Task 17/25] Current/Best: 16.50/ 23.39 GFLOPS | Progress: (16/20) | 11.65 s
[Task 17/25] Current/Best: 10.03/ 23.39 GFLOPS | Progress: (20/20) | 13.77 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.27/ 17.92 GFLOPS | Progress: (4/20) | 3.69 s
[Task 18/25] Current/Best: 10.51/ 19.67 GFLOPS | Progress: (8/20) | 7.08 s
[Task 18/25] Current/Best: 19.11/ 19.67 GFLOPS | Progress: (12/20) | 9.02 s
[Task 18/25] Current/Best: 10.08/ 19.67 GFLOPS | Progress: (16/20) | 12.59 s
[Task 18/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (20/20) | 14.09 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.32/ 20.39 GFLOPS | Progress: (4/20) | 5.95 s
[Task 19/25] Current/Best: 2.61/ 20.39 GFLOPS | Progress: (8/20) | 9.25 s
[Task 19/25] Current/Best: 19.65/ 21.93 GFLOPS | Progress: (12/20) | 12.08 s
[Task 19/25] Current/Best: 14.15/ 21.93 GFLOPS | Progress: (16/20) | 15.02 s
[Task 19/25] Current/Best: 2.70/ 23.88 GFLOPS | Progress: (20/20) | 17.88 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.89/ 15.26 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-
[Task 20/25] Current/Best: 10.43/ 14.91 GFLOPS | Progress: (8/20) | 6.84 s
[Task 20/25] Current/Best: 2.32/ 16.78 GFLOPS | Progress: (12/20) | 10.71 s
[Task 20/25] Current/Best: 12.53/ 16.78 GFLOPS | Progress: (16/20) | 14.50 s
[Task 20/25] Current/Best: 10.90/ 21.75 GFLOPS | Progress: (20/20) | 16.62 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.72 GFLOPS | Progress: (4/20) | 3.24 s
[Task 21/25] Current/Best: 14.67/ 17.72 GFLOPS | Progress: (8/20) | 4.79 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.93 s
[Task 21/25] Current/Best: 16.59/ 17.72 GFLOPS | Progress: (16/20) | 10.39 s
[Task 21/25] Current/Best: 4.46/ 17.72 GFLOPS | Progress: (20/20) | 17.44 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.05 GFLOPS | Progress: (4/20
) | 2.69 s
[Task 22/25] Current/Best: 8.75/ 21.82 GFLOPS | Progress: (8/20) | 4.67 s
[Task 22/25] Current/Best: 20.01/ 21.82 GFLOPS | Progress: (12/20) | 6.94 s
[Task 22/25] Current/Best: 14.25/ 21.82 GFLOPS | Progress: (16/20) | 8.99 s
[Task 22/25] Current/Best: 13.45/ 21.82 GFLOPS | Progress: (20/20) | 10.72 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.59/ 20.55 GFLOPS | Progress: (4/20) | 3.28 s
[Task 23/25] Current/Best: 15.25/ 20.55 GFLOPS | Progress: (8/20) | 6.63 s
[Task 23/25] Current/Best: 21.05/ 21.74 GFLOPS | Progress: (12/20) | 8.45 s
[Task 23/25] Current/Best: 6.44/ 21.74 GFLOPS | Progress: (16/20) | 15.50 s
[Task 23/25] Current/Best: 7.81/ 21.74 GFLOPS | Progress: (20/20) | 19.69 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (4/20) | 11.81 s
[Task 24/25] Current/Best: 3.52/ 8.72 GFLOPS | Progress: (8/20) | 23.06 s
[Task 24/25] Current/Best: 4.29/ 8.72 GFLOPS | Progress: (12/20) | 33.78 s Done.
-
[Task 24/25] Current/Best: 6.22/ 8.75 GFLOPS | Progress: (16/20) | 39.17 s
[Task 24/25] Current/Best: 3.37/ 8.98 GFLOPS | Progress: (20/20) | 45.13 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.81 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 6.20/ 8.28 GFLOPS | Progress: (8/20) | 22.87 s
[Task 25/25] Current/Best: 5.97/ 8.28 GFLOPS | Progress: (12/20) | 34.16 s
[Task 25/25] Current/Best: 5.88/ 8.61 GFLOPS | Progress: (16/20) | 35.97 s
[Task 25/25] Current/Best: 2.86/ 9.26 GFLOPS | Progress: (20/20) | 46.63 s
+
[Task 20/25] Current/Best: 9.92/ 15.26 GFLOPS | Progress: (8/20) | 6.58 s
[Task 20/25] Current/Best: 2.32/ 16.71 GFLOPS | Progress: (12/20) | 10.49 s
[Task 20/25] Current/Best: 12.37/ 16.71 GFLOPS | Progress: (16/20) | 14.27 s
[Task 20/25] Current/Best: 11.60/ 22.09 GFLOPS | Progress: (20/20) | 16.35 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.70 GFLOPS | Progress: (4/20) | 3.21 s
[Task 21/25] Current/Best: 14.63/ 17.70 GFLOPS | Progress: (8/20) | 4.76 s
[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 6.90 s
[Task 21/25] Current/Best: 17.98/ 17.98 GFLOPS | Progress: (16/20) | 10.33 s
[Task 21/25] Current/Best: 4.48/ 17.98 GFLOPS | Progress: (20/20) | 17.33 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.06 GFLOPS | Progress: (4/20
) | 2.67 s
[Task 22/25] Current/Best: 8.47/ 22.07 GFLOPS | Progress: (8/20) | 4.63 s
[Task 22/25] Current/Best: 19.96/ 22.07 GFLOPS | Progress: (12/20) | 6.90 s
[Task 22/25] Current/Best: 15.56/ 22.07 GFLOPS | Progress: (16/20) | 8.93 s
[Task 22/25] Current/Best: 14.05/ 22.07 GFLOPS | Progress: (20/20) | 10.65 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.68/ 20.83 GFLOPS | Progress: (4/20) | 3.22 s
[Task 23/25] Current/Best: 14.53/ 20.83 GFLOPS | Progress: (8/20) | 6.59 s
[Task 23/25] Current/Best: 21.01/ 21.50 GFLOPS | Progress: (12/20) | 8.39 s
[Task 23/25] Current/Best: 6.47/ 21.50 GFLOPS | Progress: (16/20) | 15.41 s
[Task 23/25] Current/Best: 7.68/ 21.50 GFLOPS | Progress: (20/20) | 19.63 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.47/ 8.47 GFLOPS | Progress: (4/20) | 11.77 s
[Task 24/25] Current/Best: 3.29/ 8.47 GFLOPS | Progress: (8/20) | 23.05 s
[Task 24/25] Current/Best: 4.52/ 8.47 GFLOPS | Progress: (12/20) | 33.77 s Done.
+ Done.
+
[Task 24/25] Current/Best: 6.16/ 8.92 GFLOPS | Progress: (16/20) | 39.23 s
[Task 24/25] Current/Best: 3.36/ 8.92 GFLOPS | Progress: (20/20) | 45.17 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.77 GFLOPS | Progress: (4/20) | 11.59 s
[Task 25/25] Current/Best: 5.67/ 7.66 GFLOPS | Progress: (8/20) | 22.85 s
[Task 25/25] Current/Best: 5.89/ 7.66 GFLOPS | Progress: (12/20) | 34.15 s
[Task 25/25] Current/Best: 5.81/ 8.96 GFLOPS | Progress: (16/20) | 36.05 s
[Task 25/25] Current/Best: 2.94/ 8.96 GFLOPS | Progress: (20/20) | 46.71 s
@@ -654,7 +655,6 @@ model using optimized operators to speed up our computations.
.. code-block:: none
- Done.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 407.9202445200008, 'median': 408.0756889999975, 'std': 1.6638874360882137}
- unoptimized: {'mean': 494.0234241400003, 'median': 493.8491089500019, 'std': 1.1897826468649766}
+ optimized: {'mean': 414.435815540005, 'median': 412.760964600011, 'std': 4.959311283397323}
+ unoptimized: {'mean': 495.3543460900017, 'median': 495.1141643500023, 'std': 1.0669017038663995}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 16.085 seconds)
+ **Total running time of the script:** ( 10 minutes 16.298 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 4e9989b9e..15f58e95a 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.247e-07 secs/op
+ 1.253e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index a3ec7f89e..946f1f2ed 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xeb78c90)), stage(b, placeholder(b, 0x223b7a90)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0xc8a6300)), stage(b, placeholder(b, 0x1fbf5e80)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index dabaeba29..f613dd378 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:00.490** total execution time for **tutorial** files:
+**13:09.987** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:16.085 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:16.298 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.689 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.763 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:45.363 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:55.130 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:29.757 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.025 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.643 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.624 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.096 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.270 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.703 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.702 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.149 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.167 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 4a0ab9073..47f07a483 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.117070001389947e-06 1.0
- naive 5.9914e-06 0.7381234853184766
- parallel 6.3085e-06 0.7771893058603347
- vector 2.4579400000000004e-05 3.02811236022248
+ numpy 7.831099999293656e-06 1.0
+ naive 5.8607e-06 0.7483878383022332
+ parallel 6.0684e-06 0.774910293642956
+ vector 2.4551599999999997e-05 3.135140657406301
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017802
+ Numpy running time: 0.018842
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.480540
+ none: 3.446373
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.299520
+ blocking: 0.306107
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.337467
+ vectorization: 0.347016
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.118950
+ loop permutation: 0.128796
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.110735
+ array packing: 0.110583
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111148
+ block caching: 0.111887
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.144831
+ parallelization: 0.144885
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4805402461 1.0
- blocking 0.2995199097 0.08605558003117957
- vectorization 0.3374667398 0.09695814900521171
- loop permutation 0.11895048730000002 0.03417586894255451
- array packing 0.1107350108 0.03181546626966326
- block caching 0.1111479312 0.03193410313946032
- parallelization 0.1448306749 0.04161155012135977
+ none 3.4463731066000003 1.0
+ blocking 0.3061070871 0.08882006609028707
+ vectorization 0.3470161409 0.10069024164430844
+ loop permutation 0.1287958974 0.03737143176789203
+ array packing 0.11058321769999999 0.032086838621223815
+ block caching 0.1118868059 0.03246508791683942
+ parallelization 0.1448853388 0.04203994585569867
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.689 seconds)
+ **Total running time of the script:** ( 1 minutes 1.763 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 36b2f1f9f..6290ec675 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-bc9197836257f7217f6f0f86cee9aeb39bf641b6
+0261b8ed8b8b9c3df36964e6bbd785cfd7259b7d
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 8d648ac75..a9e12e372 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ 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 2.767 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.390 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_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 3078a6dab..5a41f96c1 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip39a44786-1d6d-4047-bfee-53dc12696a46 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.zipe3ccce3b-6b09-489e-83bc-2f56d7679beb 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 3d3a5a0b6..818f144f6 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,15 +432,13 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:01, 31.8MB/s]
- 23%|##2 | 9.36M/41.5M [00:00<00:01, 20.9MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:01, 27.8MB/s]
- 42%|####1 | 17.3M/41.5M [00:00<00:00, 25.9MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.6MB/s]
- 62%|######1 | 25.6M/41.5M [00:00<00:00, 31.2MB/s]
- 77%|#######7 | 32.0M/41.5M [00:01<00:00, 37.0MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 41.7MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 33.3MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:01, 36.1MB/s]
+ 24%|##3 | 9.77M/41.5M [00:00<00:01, 23.4MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 30.6MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 36.3MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 46.8MB/s]
+ 89%|########9 | 37.0M/41.5M [00:00<00:00, 45.9MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 39.9MB/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 ce2d006df..8c2726cc4 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,10 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 7%|6 | 3.05M/44.7M [00:00<00:01, 31.8MB/s]
- 14%|#3 | 6.08M/44.7M [00:00<00:01, 30.5MB/s]
- 69%|######9 | 30.9M/44.7M [00:00<00:00, 133MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 127MB/s]
+ 34%|###3 | 15.0M/44.7M [00:00<00:00, 157MB/s]
+ 83%|########2 | 37.0M/44.7M [00:00<00:00, 200MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 200MB/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 411386ea6..0709fdf63 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ 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 8.163 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.828 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 27430f844..f826f9180 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:04.735</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:04.364</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:08.163</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:06.390</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>01:02.767</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:02.828</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>00:38.226</p></td>
+<td><p>00:39.318</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>00:27.775</p></td>
+<td><p>00:27.258</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.124</p></td>
+<td><p>00:25.082</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>00:24.527</p></td>
+<td><p>00:24.612</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>00:21.979</p></td>
+<td><p>00:22.677</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>00:19.090</p></td>
+<td><p>00:19.874</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>00:14.714</p></td>
+<td><p>00:13.840</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>00:02.371</p></td>
+<td><p>00:02.486</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index c8f98807b..3cbf1f1e7 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9346 15.6007 16.6983 15.5188 0.4640
+ 15.6470 15.6370 15.7906 15.5861 0.0577
</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 8b0e8e32c..8238931f3 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,17 +436,16 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 2%|2 | 3.49M/170M [00:00<00:04, 36.5MB/s]
- 4%|4 | 6.97M/170M [00:00<00:04, 34.5MB/s]
- 13%|#2 | 21.8M/170M [00:00<00:01, 88.2MB/s]
- 26%|##5 | 43.8M/170M [00:00<00:00, 143MB/s]
- 40%|#### | 68.3M/170M [00:00<00:00, 184MB/s]
- 51%|#####1 | 87.4M/170M [00:00<00:00, 169MB/s]
- 62%|######2 | 106M/170M [00:00<00:00, 177MB/s]
- 73%|#######2 | 123M/170M [00:00<00:00, 130MB/s]
- 82%|########2 | 139M/170M [00:01<00:00, 139MB/s]
- 96%|#########6| 164M/170M [00:01<00:00, 169MB/s]
-100%|##########| 170M/170M [00:01<00:00, 149MB/s]
+ 7%|7 | 12.1M/170M [00:00<00:01, 127MB/s]
+ 18%|#8 | 31.0M/170M [00:00<00:00, 168MB/s]
+ 29%|##9 | 49.4M/170M [00:00<00:00, 180MB/s]
+ 40%|#### | 68.5M/170M [00:00<00:00, 188MB/s]
+ 51%|##### | 86.4M/170M [00:00<00:00, 188MB/s]
+ 62%|######2 | 105M/170M [00:00<00:00, 191MB/s]
+ 73%|#######3 | 124M/170M [00:00<00:00, 193MB/s]
+ 84%|########3 | 143M/170M [00:00<00:00, 183MB/s]
+ 94%|#########4| 160M/170M [00:00<00:00, 154MB/s]
+100%|##########| 170M/170M [00:01<00:00, 170MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: 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)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: 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').
@@ -541,7 +540,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 55.931 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 1.108 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 daa1326e2..f02d19db0 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,9 +480,14 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 37%|###6 | 5.01M/13.6M [00:00<00:00, 51.7MB/s]
- 73%|#######3 | 9.95M/13.6M [00:00<00:00, 38.8MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 36.6MB/s]
+ 10%|9 | 1.31M/13.6M [00:00<00:00, 13.7MB/s]
+ 19%|#9 | 2.62M/13.6M [00:00<00:00, 13.4MB/s]
+ 30%|### | 4.12M/13.6M [00:00<00:00, 14.2MB/s]
+ 40%|#### | 5.48M/13.6M [00:00<00:01, 7.56MB/s]
+ 55%|#####4 | 7.43M/13.6M [00:00<00:00, 10.5MB/s]
+ 70%|######9 | 9.43M/13.6M [00:00<00:00, 13.0MB/s]
+ 85%|########4 | 11.5M/13.6M [00:00<00:00, 15.3MB/s]
+100%|##########| 13.6M/13.6M [00:01<00:00, 13.9MB/s]
</pre></div>
</div>
</div>
@@ -571,7 +576,7 @@ 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)
- 90.2164 90.1745 92.2312 90.0624 0.2367
+ 90.2356 90.1851 91.9263 89.9990 0.2205
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +615,7 @@ 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 9.223 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.549 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 09627fbeb..a34917dc5 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.4009 119.3560 120.4940 118.4916 0.3963
+ 120.1575 120.1845 121.8541 118.7708 0.7848
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ 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> ( 1 minutes 51.112 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.855 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 0c81d5000..ae88bc470 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ 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 36.956 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.488 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 571c3be6a..db8cbc53a 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,24 +441,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|2 | 3600/132723 [00:00<00:03, 35997.72KB/s]
- 7%|7 | 9901/132723 [00:00<00:02, 51881.60KB/s]
- 14%|#4 | 18858/132723 [00:00<00:01, 69086.81KB/s]
- 21%|## | 27773/132723 [00:00<00:01, 77001.52KB/s]
- 27%|##6 | 35474/132723 [00:00<00:01, 76495.81KB/s]
- 33%|###3 | 44416/132723 [00:00<00:01, 80868.71KB/s]
- 40%|###9 | 52506/132723 [00:00<00:01, 50135.47KB/s]
- 46%|####6 | 61425/132723 [00:00<00:01, 58881.10KB/s]
- 52%|#####1 | 68601/132723 [00:01<00:01, 61518.90KB/s]
- 58%|#####8 | 77573/132723 [00:01<00:00, 68727.57KB/s]
- 64%|######4 | 85255/132723 [00:01<00:00, 55557.75KB/s]
- 71%|####### | 94079/132723 [00:01<00:00, 63089.49KB/s]
- 76%|#######6 | 101278/132723 [00:01<00:00, 44383.40KB/s]
- 82%|########2 | 109483/132723 [00:01<00:00, 51685.83KB/s]
- 87%|########7 | 115988/132723 [00:02<00:00, 22130.75KB/s]
- 93%|#########2| 122993/132723 [00:02<00:00, 27478.72KB/s]
- 99%|#########9| 131781/132723 [00:02<00:00, 35784.70KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 46094.31KB/s]
+ 5%|5 | 6805/132723 [00:00<00:01, 68040.49KB/s]
+ 11%|#1 | 14983/132723 [00:00<00:01, 76116.37KB/s]
+ 17%|#7 | 22595/132723 [00:00<00:03, 35265.90KB/s]
+ 23%|##3 | 30568/132723 [00:00<00:02, 45583.70KB/s]
+ 28%|##7 | 36814/132723 [00:00<00:02, 40570.75KB/s]
+ 34%|###3 | 44743/132723 [00:00<00:01, 49271.05KB/s]
+ 38%|###8 | 50852/132723 [00:01<00:02, 40437.16KB/s]
+ 44%|####4 | 58897/132723 [00:01<00:01, 48923.26KB/s]
+ 50%|##### | 66979/132723 [00:01<00:01, 56339.05KB/s]
+ 57%|#####6 | 75078/132723 [00:01<00:00, 62484.43KB/s]
+ 62%|######1 | 82169/132723 [00:01<00:00, 58183.13KB/s]
+ 68%|######7 | 90026/132723 [00:01<00:00, 63324.96KB/s]
+ 74%|#######4 | 98257/132723 [00:01<00:00, 68350.53KB/s]
+ 80%|#######9 | 105541/132723 [00:02<00:00, 54592.59KB/s]
+ 86%|########5 | 113503/132723 [00:02<00:00, 60480.75KB/s]
+ 91%|######### | 120223/132723 [00:02<00:00, 44721.80KB/s]
+ 97%|#########6| 128217/132723 [00:02<00:00, 51955.12KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 52704.65KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -501,7 +501,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.917 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.151 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 c530fb8ca..a72f18d15 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:20.224</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:22.417</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:55.931</p></td>
+<td><p>03:01.108</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:32.917</p></td>
+<td><p>02:30.151</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>01:51.112</p></td>
+<td><p>01:52.855</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>01:36.956</p></td>
+<td><p>01:34.488</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>01:09.223</p></td>
+<td><p>01:10.549</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:30.225</p></td>
+<td><p>00:29.059</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.068</p></td>
+<td><p>00:22.260</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:21.786</p></td>
+<td><p>00:21.941</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 8288d8982..e3ccc5d40 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ 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.zipd1a0b406-e3d9-445f-a0d5-6bdf695a672d 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.zip1349ce1a-fcce-4761-8b07-02c10642bb9c 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>
@@ -676,7 +676,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 35d36ed0f..57ffde147 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:40.403</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:39.412</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.242</p></td>
+<td><p>00:36.293</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>00:02.225</p></td>
+<td><p>00:02.157</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.929</p></td>
+<td><p>00:00.949</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.013</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 185f3cf13..256a00421 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ 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: 6538us [6538us] (46.06%; 46.06%)
-FoldScaleAxis: 7657us [6us] (53.94%; 53.94%)
- FoldConstant: 7651us [1576us] (53.90%; 99.93%)
- InferType: 6075us [6075us] (42.80%; 79.40%)
+InferType: 6542us [6542us] (45.59%; 45.59%)
+FoldScaleAxis: 7806us [6us] (54.41%; 54.41%)
+ FoldConstant: 7801us [1602us] (54.37%; 99.93%)
+ InferType: 6199us [6199us] (43.21%; 79.47%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ 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: 6119us [6119us] (44.41%; 44.41%)
-FoldScaleAxis: 7658us [5us] (55.59%; 55.59%)
- FoldConstant: 7653us [1583us] (55.55%; 99.94%)
- InferType: 6071us [6071us] (44.06%; 79.32%)
+InferType: 6213us [6213us] (44.61%; 44.61%)
+FoldScaleAxis: 7714us [5us] (55.39%; 55.39%)
+ FoldConstant: 7709us [1595us] (55.36%; 99.94%)
+ InferType: 6114us [6114us] (43.90%; 79.31%)
</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 37ca6e311..00113e807 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ 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: 33.071917 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.204385 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 b2e71719d..b6daded24 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ 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: 8.248792 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.873218 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 2bc0f2eb5..dca53dc58 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ 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: 0.018744
-Baseline: 3.400800
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018482
+Baseline: 3.322170
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ 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: 0.304235
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.304844
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ 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: 0.335194
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.344033
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ 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: 0.118273
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.112513
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ 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: 0.111086
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108665
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ 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: 0.111779
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110813
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145234
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144883
</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 461e88b91..729a37a38 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:34.493</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.249</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.300</p></td>
+<td><p>00:32.047</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>00:01.221</p></td>
+<td><p>00:01.224</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>00:00.971</p></td>
+<td><p>00:00.978</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 cff932259..1ac84da08 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>05:58.573</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:18.797</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</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>03:15.612</p></td>
+<td><p>03:27.004</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>01:21.830</p></td>
+<td><p>01:21.086</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:45.346</p></td>
+<td><p>00:45.292</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>00:18.245</p></td>
+<td><p>00:28.302</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>00:08.799</p></td>
+<tr class="row-odd"><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>00:08.632</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>00:08.741</p></td>
+<tr class="row-even"><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>00:08.481</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 1bb068023..4ece48c47 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
@@ -475,6 +475,9 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+</pre></div>
+</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -491,422 +494,483 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[16] = 0f32
- conv2d_nchw_1[20] = 0f32
- conv2d_nchw_1[24] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[13] = 0f32
- conv2d_nchw_1[17] = 0f32
- conv2d_nchw_1[21] = 0f32
- conv2d_nchw_1[25] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[18] = 0f32
- conv2d_nchw_1[22] = 0f32
- conv2d_nchw_1[26] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[15] = 0f32
- conv2d_nchw_1[19] = 0f32
- conv2d_nchw_1[23] = 0f32
- conv2d_nchw_1[27] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[(threadIdx.x_1*18)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 1)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 2)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 3)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 4)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 5)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 6)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 7)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 8)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 9)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 10)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 11)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 12)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 13)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 14)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 15)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 16)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 17)] = 0f32
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3)) + 142848)]
- }
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -943,7 +1007,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.316 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.361 ms
</pre></div>
</div>
</div>
@@ -973,36 +1037,36 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_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=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1021,12 +1085,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=18)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1046,376 +1110,430 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[2304];
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
- conv2d_nchw[26] = 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[15] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
- conv2d_nchw[27] = 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) {
- __syncthreads();
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[(((int)threadIdx.x) * 18)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 142848)];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ 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 i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -1452,7 +1570,7 @@ 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> ( 3 minutes 15.612 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 27.004 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 a4a553480..9e986083e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ 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)
- 9.8218 9.8302 9.8654 9.7698 0.0395
+ 9.9402 9.9441 9.9738 9.9027 0.0292
</pre></div>
</div>
</div>
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 888383fd7..6abf258bc 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ 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)
- 760.6107 761.1158 762.3256 758.3907 1.6456
+ 749.8601 749.8542 751.2388 748.4872 1.1233
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ 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 21.830 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.086 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 1af135caf..4c022ed3e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,106 +625,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = ((i.outer.inner*64) + (i.inner*16))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*64) + (i.inner*16)) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*64) + (i.inner*16)) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*64) + (i.inner*16)) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*64) + (i.inner*16)) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*64) + (i.inner*16)) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*64) + (i.inner*16)) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*64) + (i.inner*16)) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*64) + (i.inner*16)) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*64) + (i.inner*16)) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*64) + (i.inner*16)) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*64) + (i.inner*16)) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*64) + (i.inner*16)) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*64) + (i.inner*16)) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = (((i.outer.inner*64) + (i.inner*16)) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = (((i.outer.inner*64) + (i.inner*16)) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -762,7 +686,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.124 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.543 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 56ab18496..35bec3108 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:45.294</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.504</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,22 +336,22 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.259</p></td>
+<td><p>00:45.468</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>00:00.019</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>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 5f94eb742..12a4882dc 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('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, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 80.69/80.69 result: MeasureResult(costs=(0.002868899028571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8650996685028076, timestamp=1659410039.641088) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/80.69 result: Traceback (most recent call last):
+No: 9 GFLOPS: 218.51/218.51 result: MeasureResult(costs=(0.001059437227586207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1403276920318604, timestamp=1659411506.1598961) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/218.51 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.46/260.46 result: MeasureResult(costs=(0.0008888055027624309,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7665715217590332, timestamp=1659410040.5633569) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.24/260.24 result: MeasureResult(costs=(0.0008895562265193371,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7725238800048828, timestamp=1659411507.0843732) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.30/260.46 result: MeasureResult(costs=(0.0436386055,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8647127151489258, timestamp=1659410045.122671) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.35/260.46 result: MeasureResult(costs=(0.0691087085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.52761435508728, timestamp=1659410046.358635) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.25/260.24 result: MeasureResult(costs=(0.04406296375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8488798141479492, timestamp=1659411511.6304812) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/260.24 result: MeasureResult(costs=(0.0694109735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.502104997634888, timestamp=1659411512.8628416) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.00/260.46 result: MeasureResult(costs=(0.008266975642857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2550444602966309, timestamp=1659410057.4064996) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.08/260.24 result: MeasureResult(costs=(0.008245470285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3395006656646729, timestamp=1659411523.9112604) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.46 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.24 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001296
+Time cost of this operator: 0.001244
</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 eb7ec650c..0cd28f078 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## 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 310.3 98.727 (1, 2, 10, 10, 3) 2 1 [310.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.045 0.969 (1, 6, 10, 10) 1 1 [3.045]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.304 (1, 1, 10, 10, 3) 1 1 [0.957]
-Total_time - 314.302 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.2 98.731 (1, 2, 10, 10, 3) 2 1 [313.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.071 0.968 (1, 6, 10, 10) 1 1 [3.071]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.301 (1, 1, 10, 10, 3) 1 1 [0.955]
+Total_time - 317.226 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## 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 79.375 96.606 (1, 6, 10, 10, 1) 2 1 [79.375]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.823 2.219 (1, 6, 10, 10) 1 1 [1.823]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 1.174 (1, 1, 10, 10, 3) 1 1 [0.965]
-Total_time - 82.163 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.375 96.637 (1, 6, 10, 10, 1) 2 1 [79.375]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.798 2.188 (1, 6, 10, 10) 1 1 [1.798]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 1.175 (1, 1, 10, 10, 3) 1 1 [0.965]
+Total_time - 82.138 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index bc1f11d5b..36fff0eda 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ 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/tmpwigspvrk/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmps44wm1mc/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpwigspvrk/images/target contains 8144 images
-/tmp/tmpwigspvrk/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], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmps44wm1mc/images/target contains 8144 images
+/tmp/tmps44wm1mc/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ 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 - 55s - loss: 0.2141 - accuracy: 0.9277 - val_loss: 0.1536 - val_accuracy: 0.9547
+328/328 - 55s - loss: 0.2099 - accuracy: 0.9278 - val_loss: 0.1353 - val_accuracy: 0.9573
Epoch 2/3
-328/328 - 52s - loss: 0.1017 - accuracy: 0.9622 - val_loss: 0.1156 - val_accuracy: 0.9653
+328/328 - 52s - loss: 0.0958 - accuracy: 0.9649 - val_loss: 0.1169 - val_accuracy: 0.9687
Epoch 3/3
-328/328 - 52s - loss: 0.0657 - accuracy: 0.9754 - val_loss: 0.1009 - val_accuracy: 0.9698
+328/328 - 56s - loss: 0.0674 - accuracy: 0.9757 - val_loss: 0.1150 - val_accuracy: 0.9649
-<keras.callbacks.History object at 0x7f1efa831950>
+<keras.callbacks.History object at 0x7fc9f44670d0>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ 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> ( 5 minutes 17.887 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 47.210 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 37a7b79b9..e9c9a7972 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>06:11.301</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:38.758</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:17.887</p></td>
+<td><p>04:47.210</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.107</p></td>
+<td><p>00:41.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.962</p></td>
+<td><p>00:07.220</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.343</p></td>
+<td><p>00:03.302</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 52317423b..98e83e4e8 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:42.224</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:41.307</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</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>00:30.836</p></td>
+<td><p>00:30.129</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.829</p></td>
+<td><p>00:09.685</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>00:01.552</p></td>
+<td><p>00:01.485</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 672236453..90c53bae7 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ 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 0x7f1e64208c20>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fc9f58a3560>
</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 972dc8dd9..17d6c66b4 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.074</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:03.958</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.893</p></td>
+<td><p>00:01.855</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.951</p></td>
+<td><p>00:00.884</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>00:00.532</p></td>
+<td><p>00:00.522</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>00:00.517</p></td>
+<td><p>00:00.508</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>00:00.100</p></td>
+<td><p>00:00.107</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>00:00.041</p></td>
+<td><p>00:00.040</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index c2365c9e5..d1b48beb7 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpq2xm5tv_/input0.cc'\nsource_filename = \"/tmp/tmpq2xm5tv_/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpi38qfaam/input0.cc'\nsource_filename = \"/tmp/tmpi38qfaam/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 3153785d7..aa2238b85 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,7 +224,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index f1578cc49..2457d2e4e 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ 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>
@@ -1886,7 +1886,7 @@ 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 092cc9eed..d2679ce40 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/bc9197836/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 db5d1cd1c..cd70d1a2e 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/bc9197836/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 5ae25f29a..f0a9e5edb 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/bc9197836/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 f9dbcb979..f6ab1031a 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/bc9197836/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 458e3ccdf..05abc1171 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/bc9197836/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 c4c7fc51c..a05e93e42 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/bc9197836/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 9386d00b3..972431a53 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/bc9197836/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 b01843fd1..bcd4e06d2 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/bc9197836/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L1140">runtime.ts:1140</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/bc9197836/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 7ddda01fd..a8da99fcc 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/bc9197836/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 03c3a01b9..1b6cbe9d0 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/bc9197836/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 56aed4726..5d8087cff 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/bc9197836/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 1037ae347..b12906aea 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/bc9197836/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 ecddee89a..6271f5d70 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/bc9197836/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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/bc9197836/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/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 73c12b84b..23e69e744 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 789f12e23..3f2ba2282 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index d48e3e0e6..4679d9cbb 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index bdc4b4e87..596dbd574 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index e06871309..11e5d72fe 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 975f39b2a..8e29d5e9a 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index c72dd78df..89a7b9374 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 7e438fee8..6edd2ac32 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index e7f2c7968..9b433cdbe 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<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">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 848b8cf9f..7a15d81d0 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<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/bc9197836/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 4cc6e4130..efeb35fa3 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<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">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bc9197836/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</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/bc9197836/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/0261b8ed8/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 5e0d219a2..bcd0360d0 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 3d1de2043..eae069c1e 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:21.245</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.023</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:21.239</p></td>
+<td><p>00:21.017</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index b7ff9f2ce..02d3ba249 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
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 23.13s!
+resnet18_v1 inference graph built in 22.67s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 391255437..6f87d6044 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.02s!
+yolov3-tiny inference graph built in 16.09s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 720898cd4..27738e720 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:32.541</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.445</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.230</p></td>
+<td><p>00:48.666</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:43.311</p></td>
+<td><p>00:42.778</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 2bd2fa8eb..1d7370ad8 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.204</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.252</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.806</p></td>
+<td><p>00:02.868</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.399</p></td>
+<td><p>00:00.385</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index c0e42a115..7bc43d760 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.714</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.694</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.382</p></td>
+<td><p>00:00.370</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.332</p></td>
+<td><p>00:00.324</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 2705d50d1..c32b445ff 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -566,7 +566,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.551 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.898 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index f6e0d783c..0a562772b 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -668,16 +668,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.61/10.61 result: MeasureResult(costs=(0.025294538999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5397012233734131, timestamp=1659408838.7096004) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.93/10.61 result: MeasureResult(costs=(0.0915333492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6175546646118164, timestamp=1659408840.3378012) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022695635999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6015610694885254, timestamp=1659408841.3872285) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.42/11.83 result: MeasureResult(costs=(0.1894552552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1577374935150146, timestamp=1659408845.1159136) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.54/11.83 result: MeasureResult(costs=(0.07583382860000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3500444889068604, timestamp=1659408846.5962448) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.54/11.83 result: MeasureResult(costs=(0.1742443344,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.945324182510376, timestamp=1659408849.5857105) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.84/11.83 result: MeasureResult(costs=(0.32029403320000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.24799919128418, timestamp=1659408855.3940082) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.19/11.83 result: MeasureResult(costs=(0.026343662,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5618143081665039, timestamp=1659408855.9780061) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.56/11.83 result: MeasureResult(costs=(0.172617332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.867321729660034, timestamp=1659408858.9649155) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.49/11.83 result: MeasureResult(costs=(0.1077967698,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8286898136138916, timestamp=1659408860.8513565) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.56/10.56 result: MeasureResult(costs=(0.025424939,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.544111967086792, timestamp=1659410295.3199446) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.94/10.56 result: MeasureResult(costs=(0.09141061539999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6080753803253174, timestamp=1659410297.4769225) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.022680726999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5954163074493408, timestamp=1659410298.046174) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.85/11.84 result: MeasureResult(costs=(0.1454228474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4518978595733643, timestamp=1659410301.0675182) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.66/11.84 result: MeasureResult(costs=(0.0733388552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3104808330535889, timestamp=1659410302.5029118) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.79/11.84 result: MeasureResult(costs=(0.149961646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.52341628074646, timestamp=1659410305.5947134) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.84 result: MeasureResult(costs=(0.307517514,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.038498878479004, timestamp=1659410310.6786737) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.64/11.84 result: MeasureResult(costs=(0.025228234999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5508103370666504, timestamp=1659410311.245852) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.90/11.84 result: MeasureResult(costs=(0.141155082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3602657318115234, timestamp=1659410313.7249591) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.78/11.84 result: MeasureResult(costs=(0.0966290474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.652329683303833, timestamp=1659410315.4350224) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index fc05ff8c6..6f958cd1e 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -550,7 +550,7 @@ standard deviation.</p>
<span class="nb">print</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">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 494.0234241400003, 'median': 493.8491089500019, 'std': 1.1897826468649766}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 495.3543460900017, 'median': 495.1141643500023, 'std': 1.0669017038663995}
</pre></div>
</div>
</div>
@@ -705,178 +705,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (4/20) | 6.30 s
-[Task 1/25] Current/Best: 6.15/ 17.49 GFLOPS | Progress: (8/20) | 9.22 s
-[Task 1/25] Current/Best: 11.55/ 22.78 GFLOPS | Progress: (12/20) | 11.64 s
-[Task 1/25] Current/Best: 16.87/ 22.80 GFLOPS | Progress: (16/20) | 13.33 s
-[Task 1/25] Current/Best: 11.59/ 23.94 GFLOPS | Progress: (20/20) | 15.05 s Done.
+[Task 1/25] Current/Best: 17.46/ 17.46 GFLOPS | Progress: (4/20) | 6.21 s
+[Task 1/25] Current/Best: 6.16/ 17.46 GFLOPS | Progress: (8/20) | 9.23 s
+[Task 1/25] Current/Best: 11.55/ 22.77 GFLOPS | Progress: (12/20) | 11.65 s
+[Task 1/25] Current/Best: 16.88/ 22.85 GFLOPS | Progress: (16/20) | 13.32 s
+[Task 1/25] Current/Best: 11.59/ 23.92 GFLOPS | Progress: (20/20) | 15.09 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.29/ 13.00 GFLOPS | Progress: (4/20) | 3.77 s
-[Task 2/25] Current/Best: 14.09/ 18.91 GFLOPS | Progress: (8/20) | 5.09 s
-[Task 2/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (12/20) | 6.41 s
-[Task 2/25] Current/Best: 12.44/ 20.59 GFLOPS | Progress: (16/20) | 7.69 s
-[Task 2/25] Current/Best: 19.49/ 20.59 GFLOPS | Progress: (20/20) | 9.23 s Done.
+[Task 2/25] Current/Best: 12.22/ 13.09 GFLOPS | Progress: (4/20) | 3.75 s
+[Task 2/25] Current/Best: 14.30/ 18.64 GFLOPS | Progress: (8/20) | 5.05 s
+[Task 2/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (12/20) | 6.40 s
+[Task 2/25] Current/Best: 12.11/ 21.17 GFLOPS | Progress: (16/20) | 7.65 s
+[Task 2/25] Current/Best: 18.72/ 21.17 GFLOPS | Progress: (20/20) | 9.25 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 10.60 GFLOPS | Progress: (4/20) | 5.85 s
-[Task 3/25] Current/Best: 15.59/ 16.83 GFLOPS | Progress: (8/20) | 7.76 s
-[Task 3/25] Current/Best: 14.92/ 16.83 GFLOPS | Progress: (12/20) | 9.48 s
-[Task 3/25] Current/Best: 7.22/ 23.82 GFLOPS | Progress: (16/20) | 11.38 s
-[Task 3/25] Current/Best: 12.65/ 23.82 GFLOPS | Progress: (20/20) | 15.90 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.59 GFLOPS | Progress: (4/20) | 5.84 s
+[Task 3/25] Current/Best: 15.60/ 16.89 GFLOPS | Progress: (8/20) | 7.75 s
+[Task 3/25] Current/Best: 14.91/ 16.89 GFLOPS | Progress: (12/20) | 9.48 s
+[Task 3/25] Current/Best: 7.19/ 23.83 GFLOPS | Progress: (16/20) | 11.41 s
+[Task 3/25] Current/Best: 12.63/ 23.83 GFLOPS | Progress: (20/20) | 15.90 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.55/ 20.50 GFLOPS | Progress: (4/20) | 2.39 s
-[Task 4/25] Current/Best: 6.42/ 20.50 GFLOPS | Progress: (8/20) | 6.71 s
-[Task 4/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (12/20) | 11.29 s
-[Task 4/25] Current/Best: 16.64/ 22.19 GFLOPS | Progress: (16/20) | 13.49 s
-[Task 4/25] Current/Best: 12.87/ 22.19 GFLOPS | Progress: (20/20) | 15.49 s Done.
+[Task 4/25] Current/Best: 9.55/ 20.41 GFLOPS | Progress: (4/20) | 2.37 s
+[Task 4/25] Current/Best: 6.84/ 20.41 GFLOPS | Progress: (8/20) | 6.69 s
+[Task 4/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (12/20) | 11.19 s
+[Task 4/25] Current/Best: 17.37/ 22.56 GFLOPS | Progress: (16/20) | 13.42 s
+[Task 4/25] Current/Best: 13.29/ 22.56 GFLOPS | Progress: (20/20) | 15.44 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.70/ 10.30 GFLOPS | Progress: (4/20) | 2.60 s
-[Task 5/25] Current/Best: 11.68/ 11.68 GFLOPS | Progress: (8/20) | 4.66 s
-[Task 5/25] Current/Best: 11.68/ 18.06 GFLOPS | Progress: (12/20) | 7.76 s
-[Task 5/25] Current/Best: 11.82/ 22.72 GFLOPS | Progress: (16/20) | 9.17 s
-[Task 5/25] Current/Best: 12.01/ 22.72 GFLOPS | Progress: (20/20) | 11.03 s Done.
+[Task 5/25] Current/Best: 9.71/ 10.10 GFLOPS | Progress: (4/20) | 2.60 s
+[Task 5/25] Current/Best: 11.71/ 12.61 GFLOPS | Progress: (8/20) | 4.67 s
+[Task 5/25] Current/Best: 11.67/ 18.12 GFLOPS | Progress: (12/20) | 7.73 s
+[Task 5/25] Current/Best: 11.77/ 22.66 GFLOPS | Progress: (16/20) | 9.15 s
+[Task 5/25] Current/Best: 12.11/ 22.66 GFLOPS | Progress: (20/20) | 11.01 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.11/ 20.73 GFLOPS | Progress: (4/20) | 3.97 s
-[Task 6/25] Current/Best: 19.00/ 20.73 GFLOPS | Progress: (8/20) | 5.74 s
-[Task 6/25] Current/Best: 13.27/ 20.73 GFLOPS | Progress: (12/20) | 7.67 s
-[Task 6/25] Current/Best: 19.92/ 20.73 GFLOPS | Progress: (16/20) | 9.90 s
-[Task 6/25] Current/Best: 3.76/ 20.73 GFLOPS | Progress: (20/20) | 12.41 s Done.
+[Task 6/25] Current/Best: 12.12/ 20.69 GFLOPS | Progress: (4/20) | 3.97 s
+[Task 6/25] Current/Best: 19.04/ 20.69 GFLOPS | Progress: (8/20) | 5.72 s
+[Task 6/25] Current/Best: 13.34/ 20.69 GFLOPS | Progress: (12/20) | 7.64 s
+[Task 6/25] Current/Best: 20.03/ 20.69 GFLOPS | Progress: (16/20) | 9.86 s
+[Task 6/25] Current/Best: 3.73/ 20.69 GFLOPS | Progress: (20/20) | 12.41 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 10.01/ 13.01 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 7/25] Current/Best: 20.33/ 21.16 GFLOPS | Progress: (8/20) | 5.09 s
-[Task 7/25] Current/Best: 16.08/ 21.16 GFLOPS | Progress: (12/20) | 7.02 s
-[Task 7/25] Current/Best: 12.26/ 21.16 GFLOPS | Progress: (16/20) | 9.06 s
-[Task 7/25] Current/Best: 6.38/ 21.76 GFLOPS | Progress: (20/20) | 11.52 s Done.
+[Task 7/25] Current/Best: 11.17/ 12.85 GFLOPS | Progress: (4/20) | 3.61 s
+[Task 7/25] Current/Best: 20.14/ 21.18 GFLOPS | Progress: (8/20) | 5.12 s
+[Task 7/25] Current/Best: 14.39/ 21.18 GFLOPS | Progress: (12/20) | 7.05 s
+[Task 7/25] Current/Best: 12.25/ 21.18 GFLOPS | Progress: (16/20) | 9.10 s
+[Task 7/25] Current/Best: 6.32/ 21.83 GFLOPS | Progress: (20/20) | 11.54 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.69/ 13.67 GFLOPS | Progress: (4/20) | 2.91 s
-[Task 8/25] Current/Best: 9.35/ 13.67 GFLOPS | Progress: (8/20) | 7.59 s
-[Task 8/25] Current/Best: 12.50/ 13.67 GFLOPS | Progress: (12/20) | 13.65 s
-[Task 8/25] Current/Best: 18.77/ 18.77 GFLOPS | Progress: (16/20) | 15.76 s
-[Task 8/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (20/20) | 22.28 s Done.
+[Task 8/25] Current/Best: 9.86/ 13.65 GFLOPS | Progress: (4/20) | 2.91 s
+[Task 8/25] Current/Best: 9.56/ 13.65 GFLOPS | Progress: (8/20) | 7.68 s
+[Task 8/25] Current/Best: 12.57/ 13.65 GFLOPS | Progress: (12/20) | 13.78 s
+[Task 8/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (16/20) | 15.88 s
+[Task 8/25] Current/Best: 19.49/ 19.49 GFLOPS | Progress: (20/20) | 22.36 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.35/ 15.93 GFLOPS | Progress: (4/20) | 11.95 s
-[Task 9/25] Current/Best: 23.61/ 23.61 GFLOPS | Progress: (8/20) | 13.77 s
-[Task 9/25] Current/Best: 8.28/ 23.61 GFLOPS | Progress: (12/20) | 16.16 s
-[Task 9/25] Current/Best: 17.98/ 23.61 GFLOPS | Progress: (16/20) | 18.72 s
-[Task 9/25] Current/Best: 9.00/ 23.61 GFLOPS | Progress: (20/20) | 26.32 s
+[Task 9/25] Current/Best: 14.34/ 15.76 GFLOPS | Progress: (4/20) | 11.95 s
+[Task 9/25] Current/Best: 23.19/ 23.19 GFLOPS | Progress: (8/20) | 13.77 s
+[Task 9/25] Current/Best: 8.24/ 23.19 GFLOPS | Progress: (12/20) | 16.13 s
+[Task 9/25] Current/Best: 17.90/ 23.19 GFLOPS | Progress: (16/20) | 18.69 s
+[Task 9/25] Current/Best: 9.20/ 23.19 GFLOPS | Progress: (20/20) | 26.44 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (4/20) | 2.60 s
-[Task 10/25] Current/Best: 15.47/ 18.15 GFLOPS | Progress: (8/20) | 4.17 s
-[Task 10/25] Current/Best: 12.43/ 19.02 GFLOPS | Progress: (12/20) | 5.70 s
-[Task 10/25] Current/Best: 18.77/ 20.28 GFLOPS | Progress: (16/20) | 6.81 s
-[Task 10/25] Current/Best: 8.87/ 20.28 GFLOPS | Progress: (20/20) | 8.37 s Done.
+[Task 10/25] Current/Best: 18.34/ 18.34 GFLOPS | Progress: (4/20) | 2.58 s
+[Task 10/25] Current/Best: 15.52/ 18.34 GFLOPS | Progress: (8/20) | 4.16 s
+[Task 10/25] Current/Best: 12.63/ 18.85 GFLOPS | Progress: (12/20) | 5.69 s
+[Task 10/25] Current/Best: 19.21/ 20.34 GFLOPS | Progress: (16/20) | 6.79 s
+[Task 10/25] Current/Best: 8.88/ 20.34 GFLOPS | Progress: (20/20) | 8.31 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 11.79/ 18.17 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 11/25] Current/Best: 16.86/ 18.17 GFLOPS | Progress: (8/20) | 6.04 s
-[Task 11/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (12/20) | 8.08 s
-[Task 11/25] Current/Best: 13.47/ 21.14 GFLOPS | Progress: (16/20) | 10.83 s
-[Task 11/25] Current/Best: 19.45/ 21.54 GFLOPS | Progress: (20/20) | 12.88 s Done.
+[Task 11/25] Current/Best: 11.81/ 18.22 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 11/25] Current/Best: 16.75/ 18.22 GFLOPS | Progress: (8/20) | 6.02 s
+[Task 11/25] Current/Best: 16.58/ 18.22 GFLOPS | Progress: (12/20) | 8.10 s
+[Task 11/25] Current/Best: 13.37/ 21.19 GFLOPS | Progress: (16/20) | 10.87 s
+[Task 11/25] Current/Best: 19.42/ 21.54 GFLOPS | Progress: (20/20) | 12.90 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.81/ 17.94 GFLOPS | Progress: (4/20) | 5.44 s
-[Task 12/25] Current/Best: 5.21/ 17.94 GFLOPS | Progress: (8/20) | 9.15 s
-[Task 12/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (12/20) | 11.16 s
-[Task 12/25] Current/Best: 15.27/ 18.81 GFLOPS | Progress: (16/20) | 13.94 s
-[Task 12/25] Current/Best: 15.15/ 18.86 GFLOPS | Progress: (20/20) | 15.86 s Done.
+[Task 12/25] Current/Best: 7.84/ 18.02 GFLOPS | Progress: (4/20) | 5.38 s
+[Task 12/25] Current/Best: 5.24/ 18.02 GFLOPS | Progress: (8/20) | 9.10 s
+[Task 12/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (12/20) | 11.08 s
+[Task 12/25] Current/Best: 15.22/ 18.86 GFLOPS | Progress: (16/20) | 13.89 s
+[Task 12/25] Current/Best: 15.08/ 18.86 GFLOPS | Progress: (20/20) | 15.81 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.74/ 17.32 GFLOPS | Progress: (4/20) | 3.73 s
-[Task 13/25] Current/Best: 16.04/ 20.75 GFLOPS | Progress: (8/20) | 6.17 s
-[Task 13/25] Current/Best: 19.44/ 21.50 GFLOPS | Progress: (12/20) | 9.12 s
-[Task 13/25] Current/Best: 12.21/ 21.50 GFLOPS | Progress: (16/20) | 12.55 s
-[Task 13/25] Current/Best: 18.76/ 21.50 GFLOPS | Progress: (20/20) | 14.81 s Done.
+[Task 13/25] Current/Best: 8.02/ 17.27 GFLOPS | Progress: (4/20) | 3.67 s
+[Task 13/25] Current/Best: 16.04/ 20.90 GFLOPS | Progress: (8/20) | 6.13 s
+[Task 13/25] Current/Best: 19.60/ 21.70 GFLOPS | Progress: (12/20) | 9.00 s
+[Task 13/25] Current/Best: 12.32/ 21.70 GFLOPS | Progress: (16/20) | 12.42 s
+[Task 13/25] Current/Best: 18.51/ 21.70 GFLOPS | Progress: (20/20) | 14.67 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.60/ 13.60 GFLOPS | Progress: (4/20) | 3.39 s
-[Task 14/25] Current/Best: 5.97/ 13.60 GFLOPS | Progress: (8/20) | 5.59 s
-[Task 14/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (12/20) | 8.16 s
-[Task 14/25] Current/Best: 15.53/ 20.34 GFLOPS | Progress: (16/20) | 9.82 s Done.
+[Task 14/25] Current/Best: 13.61/ 13.61 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 14/25] Current/Best: 6.13/ 13.61 GFLOPS | Progress: (8/20) | 5.51 s
+[Task 14/25] Current/Best: 19.57/ 19.57 GFLOPS | Progress: (12/20) | 8.05 s
+[Task 14/25] Current/Best: 16.09/ 19.57 GFLOPS | Progress: (16/20) | 9.70 s Done.
-[Task 14/25] Current/Best: 17.18/ 20.34 GFLOPS | Progress: (20/20) | 11.55 s
+[Task 14/25] Current/Best: 17.32/ 19.57 GFLOPS | Progress: (20/20) | 11.43 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.14/ 17.65 GFLOPS | Progress: (4/20) | 2.73 s
-[Task 15/25] Current/Best: 13.87/ 18.10 GFLOPS | Progress: (8/20) | 4.06 s
-[Task 15/25] Current/Best: 10.41/ 22.22 GFLOPS | Progress: (12/20) | 6.14 s
-[Task 15/25] Current/Best: 20.39/ 22.22 GFLOPS | Progress: (16/20) | 9.11 s
-[Task 15/25] Current/Best: 9.72/ 22.22 GFLOPS | Progress: (20/20) | 10.08 s
+[Task 15/25] Current/Best: 16.15/ 17.60 GFLOPS | Progress: (4/20) | 2.69 s
+[Task 15/25] Current/Best: 14.49/ 18.10 GFLOPS | Progress: (8/20) | 4.02 s
+[Task 15/25] Current/Best: 10.37/ 22.23 GFLOPS | Progress: (12/20) | 6.06 s
+[Task 15/25] Current/Best: 20.44/ 22.23 GFLOPS | Progress: (16/20) | 8.99 s
+[Task 15/25] Current/Best: 9.69/ 22.23 GFLOPS | Progress: (20/20) | 9.96 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.87/ 20.87 GFLOPS | Progress: (4/20) | 2.95 s
-[Task 16/25] Current/Best: 3.03/ 20.87 GFLOPS | Progress: (8/20) | 4.57 s
-[Task 16/25] Current/Best: 19.55/ 20.87 GFLOPS | Progress: (12/20) | 5.78 s
-[Task 16/25] Current/Best: 18.56/ 20.87 GFLOPS | Progress: (16/20) | 7.12 s
-[Task 16/25] Current/Best: 10.01/ 21.97 GFLOPS | Progress: (20/20) | 9.17 s Done.
+[Task 16/25] Current/Best: 20.24/ 20.24 GFLOPS | Progress: (4/20) | 2.94 s
+[Task 16/25] Current/Best: 3.04/ 20.24 GFLOPS | Progress: (8/20) | 4.56 s
+[Task 16/25] Current/Best: 19.57/ 20.24 GFLOPS | Progress: (12/20) | 5.78 s
+[Task 16/25] Current/Best: 17.54/ 20.24 GFLOPS | Progress: (16/20) | 7.14 s
+[Task 16/25] Current/Best: 10.05/ 22.18 GFLOPS | Progress: (20/20) | 9.20 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.26/ 18.85 GFLOPS | Progress: (4/20) | 4.72 s
-[Task 17/25] Current/Best: 14.37/ 23.26 GFLOPS | Progress: (8/20) | 7.59 s
-[Task 17/25] Current/Best: 16.77/ 23.26 GFLOPS | Progress: (12/20) | 9.66 s
-[Task 17/25] Current/Best: 16.52/ 23.26 GFLOPS | Progress: (16/20) | 11.82 s
-[Task 17/25] Current/Best: 10.03/ 23.26 GFLOPS | Progress: (20/20) | 13.94 s Done.
+[Task 17/25] Current/Best: 13.16/ 18.75 GFLOPS | Progress: (4/20) | 4.71 s
+[Task 17/25] Current/Best: 14.35/ 23.39 GFLOPS | Progress: (8/20) | 7.45 s
+[Task 17/25] Current/Best: 16.91/ 23.39 GFLOPS | Progress: (12/20) | 9.50 s
+[Task 17/25] Current/Best: 16.50/ 23.39 GFLOPS | Progress: (16/20) | 11.65 s
+[Task 17/25] Current/Best: 10.03/ 23.39 GFLOPS | Progress: (20/20) | 13.77 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.21/ 18.19 GFLOPS | Progress: (4/20) | 3.71 s
-[Task 18/25] Current/Best: 10.57/ 19.87 GFLOPS | Progress: (8/20) | 7.14 s
-[Task 18/25] Current/Best: 19.24/ 19.87 GFLOPS | Progress: (12/20) | 9.06 s
-[Task 18/25] Current/Best: 10.08/ 19.87 GFLOPS | Progress: (16/20) | 12.68 s
-[Task 18/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (20/20) | 14.20 s Done.
+[Task 18/25] Current/Best: 11.27/ 17.92 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 18/25] Current/Best: 10.51/ 19.67 GFLOPS | Progress: (8/20) | 7.08 s
+[Task 18/25] Current/Best: 19.11/ 19.67 GFLOPS | Progress: (12/20) | 9.02 s
+[Task 18/25] Current/Best: 10.08/ 19.67 GFLOPS | Progress: (16/20) | 12.59 s
+[Task 18/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (20/20) | 14.09 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.05/ 20.16 GFLOPS | Progress: (4/20) | 6.19 s
-[Task 19/25] Current/Best: 2.61/ 20.16 GFLOPS | Progress: (8/20) | 9.47 s
-[Task 19/25] Current/Best: 17.88/ 20.91 GFLOPS | Progress: (12/20) | 12.31 s
-[Task 19/25] Current/Best: 15.37/ 21.17 GFLOPS | Progress: (16/20) | 15.19 s
-[Task 19/25] Current/Best: 2.70/ 22.81 GFLOPS | Progress: (20/20) | 17.98 s Done.
+[Task 19/25] Current/Best: 7.32/ 20.39 GFLOPS | Progress: (4/20) | 5.95 s
+[Task 19/25] Current/Best: 2.61/ 20.39 GFLOPS | Progress: (8/20) | 9.25 s
+[Task 19/25] Current/Best: 19.65/ 21.93 GFLOPS | Progress: (12/20) | 12.08 s
+[Task 19/25] Current/Best: 14.15/ 21.93 GFLOPS | Progress: (16/20) | 15.02 s
+[Task 19/25] Current/Best: 2.70/ 23.88 GFLOPS | Progress: (20/20) | 17.88 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.78/ 14.91 GFLOPS | Progress: (4/20) | 3.40 s Done.
+[Task 20/25] Current/Best: 8.89/ 15.26 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-[Task 20/25] Current/Best: 10.43/ 14.91 GFLOPS | Progress: (8/20) | 6.84 s
-[Task 20/25] Current/Best: 2.32/ 16.78 GFLOPS | Progress: (12/20) | 10.71 s
-[Task 20/25] Current/Best: 12.53/ 16.78 GFLOPS | Progress: (16/20) | 14.50 s
-[Task 20/25] Current/Best: 10.90/ 21.75 GFLOPS | Progress: (20/20) | 16.62 s
+[Task 20/25] Current/Best: 9.92/ 15.26 GFLOPS | Progress: (8/20) | 6.58 s
+[Task 20/25] Current/Best: 2.32/ 16.71 GFLOPS | Progress: (12/20) | 10.49 s
+[Task 20/25] Current/Best: 12.37/ 16.71 GFLOPS | Progress: (16/20) | 14.27 s
+[Task 20/25] Current/Best: 11.60/ 22.09 GFLOPS | Progress: (20/20) | 16.35 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.41/ 17.72 GFLOPS | Progress: (4/20) | 3.24 s
-[Task 21/25] Current/Best: 14.67/ 17.72 GFLOPS | Progress: (8/20) | 4.79 s
-[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.93 s
-[Task 21/25] Current/Best: 16.59/ 17.72 GFLOPS | Progress: (16/20) | 10.39 s
-[Task 21/25] Current/Best: 4.46/ 17.72 GFLOPS | Progress: (20/20) | 17.44 s
+[Task 21/25] Current/Best: 6.42/ 17.70 GFLOPS | Progress: (4/20) | 3.21 s
+[Task 21/25] Current/Best: 14.63/ 17.70 GFLOPS | Progress: (8/20) | 4.76 s
+[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 6.90 s
+[Task 21/25] Current/Best: 17.98/ 17.98 GFLOPS | Progress: (16/20) | 10.33 s
+[Task 21/25] Current/Best: 4.48/ 17.98 GFLOPS | Progress: (20/20) | 17.33 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 17.05 GFLOPS | Progress: (4/20) | 2.69 s
-[Task 22/25] Current/Best: 8.75/ 21.82 GFLOPS | Progress: (8/20) | 4.67 s
-[Task 22/25] Current/Best: 20.01/ 21.82 GFLOPS | Progress: (12/20) | 6.94 s
-[Task 22/25] Current/Best: 14.25/ 21.82 GFLOPS | Progress: (16/20) | 8.99 s
-[Task 22/25] Current/Best: 13.45/ 21.82 GFLOPS | Progress: (20/20) | 10.72 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.06 GFLOPS | Progress: (4/20) | 2.67 s
+[Task 22/25] Current/Best: 8.47/ 22.07 GFLOPS | Progress: (8/20) | 4.63 s
+[Task 22/25] Current/Best: 19.96/ 22.07 GFLOPS | Progress: (12/20) | 6.90 s
+[Task 22/25] Current/Best: 15.56/ 22.07 GFLOPS | Progress: (16/20) | 8.93 s
+[Task 22/25] Current/Best: 14.05/ 22.07 GFLOPS | Progress: (20/20) | 10.65 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.59/ 20.55 GFLOPS | Progress: (4/20) | 3.28 s
-[Task 23/25] Current/Best: 15.25/ 20.55 GFLOPS | Progress: (8/20) | 6.63 s
-[Task 23/25] Current/Best: 21.05/ 21.74 GFLOPS | Progress: (12/20) | 8.45 s
-[Task 23/25] Current/Best: 6.44/ 21.74 GFLOPS | Progress: (16/20) | 15.50 s
-[Task 23/25] Current/Best: 7.81/ 21.74 GFLOPS | Progress: (20/20) | 19.69 s Done.
+[Task 23/25] Current/Best: 17.68/ 20.83 GFLOPS | Progress: (4/20) | 3.22 s
+[Task 23/25] Current/Best: 14.53/ 20.83 GFLOPS | Progress: (8/20) | 6.59 s
+[Task 23/25] Current/Best: 21.01/ 21.50 GFLOPS | Progress: (12/20) | 8.39 s
+[Task 23/25] Current/Best: 6.47/ 21.50 GFLOPS | Progress: (16/20) | 15.41 s
+[Task 23/25] Current/Best: 7.68/ 21.50 GFLOPS | Progress: (20/20) | 19.63 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (4/20) | 11.81 s
-[Task 24/25] Current/Best: 3.52/ 8.72 GFLOPS | Progress: (8/20) | 23.06 s
-[Task 24/25] Current/Best: 4.29/ 8.72 GFLOPS | Progress: (12/20) | 33.78 s Done.
+[Task 24/25] Current/Best: 8.47/ 8.47 GFLOPS | Progress: (4/20) | 11.77 s
+[Task 24/25] Current/Best: 3.29/ 8.47 GFLOPS | Progress: (8/20) | 23.05 s
+[Task 24/25] Current/Best: 4.52/ 8.47 GFLOPS | Progress: (12/20) | 33.77 s Done.
+ Done.
-[Task 24/25] Current/Best: 6.22/ 8.75 GFLOPS | Progress: (16/20) | 39.17 s
-[Task 24/25] Current/Best: 3.37/ 8.98 GFLOPS | Progress: (20/20) | 45.13 s Done.
+[Task 24/25] Current/Best: 6.16/ 8.92 GFLOPS | Progress: (16/20) | 39.23 s
+[Task 24/25] Current/Best: 3.36/ 8.92 GFLOPS | Progress: (20/20) | 45.17 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.81 GFLOPS | Progress: (4/20) | 11.61 s
-[Task 25/25] Current/Best: 6.20/ 8.28 GFLOPS | Progress: (8/20) | 22.87 s
-[Task 25/25] Current/Best: 5.97/ 8.28 GFLOPS | Progress: (12/20) | 34.16 s
-[Task 25/25] Current/Best: 5.88/ 8.61 GFLOPS | Progress: (16/20) | 35.97 s
-[Task 25/25] Current/Best: 2.86/ 9.26 GFLOPS | Progress: (20/20) | 46.63 s
+[Task 25/25] Current/Best: 1.55/ 2.77 GFLOPS | Progress: (4/20) | 11.59 s
+[Task 25/25] Current/Best: 5.67/ 7.66 GFLOPS | Progress: (8/20) | 22.85 s
+[Task 25/25] Current/Best: 5.89/ 7.66 GFLOPS | Progress: (12/20) | 34.15 s
+[Task 25/25] Current/Best: 5.81/ 8.96 GFLOPS | Progress: (16/20) | 36.05 s
+[Task 25/25] Current/Best: 2.94/ 8.96 GFLOPS | Progress: (20/20) | 46.71 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -923,8 +924,7 @@ model using optimized operators to speed up our computations.</p>
<a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="tvm.contrib.graph_executor.GraphModule" class="sphx-glr-backref-module-tvm-contrib-graph_executor sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">module</span></a> <span class="o">=</span> <a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="tvm.contrib.graph_executor.GraphModule" class="sphx-glr-backref-module-tvm-co [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Done.
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
</pre></div>
</div>
@@ -980,8 +980,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</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">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 407.9202445200008, 'median': 408.0756889999975, 'std': 1.6638874360882137}
-unoptimized: {'mean': 494.0234241400003, 'median': 493.8491089500019, 'std': 1.1897826468649766}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 414.435815540005, 'median': 412.760964600011, 'std': 4.959311283397323}
+unoptimized: {'mean': 495.3543460900017, 'median': 495.1141643500023, 'std': 1.0669017038663995}
</pre></div>
</div>
</div>
@@ -995,7 +995,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 16.085 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 16.298 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_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">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 6a45f8dd2..3ec41e177 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -526,7 +526,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.247e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.253e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index aad49266f..cc88183c3 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -483,7 +483,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xeb78c90)), stage(b, placeholder(b, 0x223b7a90)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xc8a6300)), stage(b, placeholder(b, 0x1fbf5e80)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 474d9ea2a..0f78956e2 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:00.490</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:09.987</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:16.085</p></td>
+<td><p>10:16.298</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.689</p></td>
+<td><p>01:01.763</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:45.363</p></td>
+<td><p>00:55.130</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:29.757</p></td>
+<td><p>00:31.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:25.643</p></td>
+<td><p>00:23.624</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.096</p></td>
+<td><p>00:01.270</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.703</p></td>
+<td><p>00:00.702</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.149</p></td>
+<td><p>00:00.167</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
@@ -375,11 +375,11 @@
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 85ab6a77f..53f0a3386 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -667,10 +667,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.117070001389947e-06 1.0
- naive 5.9914e-06 0.7381234853184766
-parallel 6.3085e-06 0.7771893058603347
- vector 2.4579400000000004e-05 3.02811236022248
+ numpy 7.831099999293656e-06 1.0
+ naive 5.8607e-06 0.7483878383022332
+parallel 6.0684e-06 0.774910293642956
+ vector 2.4551599999999997e-05 3.135140657406301
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -986,7 +986,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</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: 0.017802
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018842
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1029,7 +1029,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.480540
+none: 3.446373
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1096,7 +1096,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.299520
+blocking: 0.306107
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1157,7 +1157,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.337467
+vectorization: 0.347016
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1214,7 +1214,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.118950
+loop permutation: 0.128796
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1292,7 +1292,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.110735
+array packing: 0.110583
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1368,7 +1368,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.111148
+block caching: 0.111887
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1437,7 +1437,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.144831
+parallelization: 0.144885
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1499,13 +1499,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4805402461 1.0
- blocking 0.2995199097 0.08605558003117957
- vectorization 0.3374667398 0.09695814900521171
-loop permutation 0.11895048730000002 0.03417586894255451
- array packing 0.1107350108 0.03181546626966326
- block caching 0.1111479312 0.03193410313946032
- parallelization 0.1448306749 0.04161155012135977
+ none 3.4463731066000003 1.0
+ blocking 0.3061070871 0.08882006609028707
+ vectorization 0.3470161409 0.10069024164430844
+loop permutation 0.1287958974 0.03737143176789203
+ array packing 0.11058321769999999 0.032086838621223815
+ block caching 0.1118868059 0.03246508791683942
+ parallelization 0.1448853388 0.04203994585569867
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1537,7 +1537,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.689 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.763 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.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">tensor_expr_get_started.py</span></code></a></p>