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 2022/04/30 02:14:11 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@552f06ed450d59816eb3a85f7e810d9726dcce26)
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 63df9c0c9 deploying docs (apache/tvm@552f06ed450d59816eb3a85f7e810d9726dcce26)
63df9c0c9 is described below
commit 63df9c0c94d9a73214ed8410560c61140e427d72
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat Apr 30 02:14:05 2022 +0000
deploying docs (apache/tvm@552f06ed450d59816eb3a85f7e810d9726dcce26)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 5 -
.../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 | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 1683 +++++++++++++++-----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 463 +++++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 2 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 61 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 81 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 1 -
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 58 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1683 +++++++++++++++-----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 463 +++++-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 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_relay_x86.html | 176 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
115 files changed, 4155 insertions(+), 1724 deletions(-)
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 faa0c0f5e..7dc649b08 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb40a7ce6-98d9-4390-bb65-14c407749571 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipeccbf69f-00ae-4432-87a2-b99dccae5fad 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 4b4bb9413..cc520cc78 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -100,7 +100,7 @@ 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]
0%| | 16.0k/41.5M [00:00<08:09, 88.9kB/s]
0%| | 48.0k/41.5M [00:00<05:09, 141kB/s]
0%| | 96.0k/41.5M [00:00<03:39, 198kB/s]
0%| | 208k/41.5M [00:00<01:58, 364kB/s]
1%| | 304k/41.5M [00:00<01:41, 424kB/s]
1%|1 | 600k/41.5M [00:01<00:51, 836kB/s]
3%|2 | 1.16M/41.5M [00:01<00:26, 1.62MB/s]
6%|5 | 2.29M/41.5M [00:01<00:13, 3.14MB/s]
9%|9 | 3.77M/41.5M [00:01<00:08, 4.77MB/s]
13%|#2 | 5.24M/41.5M [00:01<00:06, 5.88MB/s]
16%|#6 | 6.71M/41.5M [00:02<00:05, 6.63MB/s]
20%|#9 | 8.19M/41.5M [00:02<00:04, 7.15MB/s]
23%|##3 | 9.66M/41.5M [00:02<00:04, 7.50MB/s]
27%|##6 | 11.1M/41.5M [00:02<00:04, 7.75MB/s]
30%|### | 12.6M/41.5M [00:02<00:03, 8.86MB/s]
34%|###3 | 14.0M/41.5M [00:02<00:02, 10.1MB/s]
36%|###6 | 15.1M/41.5M [00:02<00
:03, 9.11MB/s]
39%|###8 | 16.0M/41.5M [00:03<00:03, 7.81MB/s]
41%|#### | 17.0M/41.5M [00:03<00:03, 7.50MB/s]
45%|####4 | 18.5M/41.5M [00:03<00:03, 7.75MB/s]
48%|####8 | 19.9M/41.5M [00:03<00:02, 9.22MB/s]
50%|##### | 20.9M/41.5M [00:03<00:02, 9.15MB/s]
53%|#####2 | 21.8M/41.5M [00:03<00:02, 7.79MB/s]
55%|#####5 | 22.9M/41.5M [00:04<00:02, 7.23MB/s]
59%|#####8 | 24.3M/41.5M [00:04<00:02, 8.90MB/s]
62%|######2 | 25.7M/41.5M [00:04<00:01, 10.1MB/s]
65%|######4 | 26.8M/41.5M [00:04<00:01, 8.78MB/s]
67%|######6 | 27.7M/41.5M [00:04<00:01, 7.58MB/s]
69%|######9 | 28.8M/41.5M [00:04<00:01, 7.06MB/s]
73%|#######2 | 30.2M/41.5M [00:04<00:01, 8.04MB/s]
76%|#######6 | 31.7M/41.5M [00:05<00:01, 8.21MB/s]
80%|#######9 | 33.1M/41.5M [00:05<00:00, 9.51MB/s]
82%|########2 | 34.1M/41.5M [00:05<00:00, 8.99MB/s]
84%|########4 | 35.0M/41.5M [00:05<00:00, 7.68MB/s]
87%|####
####6 | 36.1M/41.5M [00:05<00:00, 7.83MB/s]
90%|######### | 37.5M/41.5M [00:05<00:00, 7.36MB/s]
94%|#########3| 39.0M/41.5M [00:06<00:00, 7.64MB/s]
98%|#########7| 40.5M/41.5M [00:06<00:00, 7.84MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 6.90MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:33, 84.6kB/s]
0%| | 48.0k/41.5M [00:00<05:34, 130kB/s]
0%| | 96.0k/41.5M [00:00<04:10, 174kB/s]
0%| | 160k/41.5M [00:00<03:09, 229kB/s]
1%| | 328k/41.5M [00:01<01:36, 447kB/s]
1%|1 | 544k/41.5M [00:01<01:04, 666kB/s]
3%|2 | 1.06M/41.5M [00:01<00:31, 1.33MB/s]
5%|4 | 1.99M/41.5M [00:01<00:16, 2.45MB/s]
8%|8 | 3.46M/41.5M [00:01<00:09, 4.11MB/s]
12%|#1 | 4.93M/41.5M [00:02<00:07, 5.14MB/s]
15%|#5 | 6.41M/41.5M [00:02<00:06, 5.87MB/s]
19%|#8 | 7.88M/41.5M [00:02<00:05, 6.31MB/s]
23%|##2 | 9.34M/41.5M [00:02<00:05, 6.54MB/s]
26%|##6 | 10.8M/41.5M [00:02<00:04, 6.78MB/s]
30%|##9 | 12.3M/41.5M [00:03<00:04, 6.93MB/s]
33%|###3 | 13.8M/41.5M [00:03<00:04, 7.10MB/s]
37%|###6 | 15.2M/41.5M [00:03<00
:03, 8.35MB/s]
39%|###8 | 16.1M/41.5M [00:03<00:03, 8.38MB/s]
41%|#### | 17.0M/41.5M [00:03<00:03, 7.00MB/s]
44%|####3 | 18.1M/41.5M [00:03<00:03, 7.99MB/s]
46%|####5 | 19.0M/41.5M [00:03<00:02, 8.13MB/s]
48%|####7 | 19.8M/41.5M [00:04<00:03, 6.49MB/s]
51%|##### | 21.1M/41.5M [00:04<00:03, 6.29MB/s]
54%|#####4 | 22.6M/41.5M [00:04<00:03, 6.52MB/s]
58%|#####7 | 24.0M/41.5M [00:04<00:02, 6.63MB/s]
61%|######1 | 25.5M/41.5M [00:05<00:02, 6.67MB/s]
65%|######4 | 26.9M/41.5M [00:05<00:01, 8.04MB/s]
67%|######7 | 27.8M/41.5M [00:05<00:01, 8.03MB/s]
69%|######9 | 28.6M/41.5M [00:05<00:01, 6.78MB/s]
72%|#######1 | 29.9M/41.5M [00:05<00:01, 7.96MB/s]
74%|#######4 | 30.7M/41.5M [00:05<00:01, 8.08MB/s]
76%|#######6 | 31.6M/41.5M [00:05<00:01, 6.58MB/s]
79%|#######9 | 32.8M/41.5M [00:05<00:01, 7.81MB/s]
81%|########1 | 33.6M/41.5M [00:06<00:01, 7.76MB/s]
83%|####
####3 | 34.5M/41.5M [00:06<00:01, 6.42MB/s]
86%|########6 | 35.8M/41.5M [00:06<00:00, 7.64MB/s]
89%|########9 | 36.9M/41.5M [00:06<00:00, 8.74MB/s]
91%|#########1| 37.9M/41.5M [00:06<00:00, 7.65MB/s]
93%|#########3| 38.7M/41.5M [00:06<00:00, 7.37MB/s]
96%|#########6| 39.9M/41.5M [00:06<00:00, 8.41MB/s]
98%|#########8| 40.7M/41.5M [00:07<00:00, 7.30MB/s]
100%|##########| 41.5M/41.5M [00:07<00:00, 6.10MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 3c7df3fa5..a1f092bf0 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -201,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.658 seconds)
+ **Total running time of the script:** ( 1 minutes 6.918 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
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 4bc8f99f1..483f8898d 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ 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]
9%|9 | 4.17M/44.7M [00:00<00:00, 43.7MB/s]
19%|#8 | 8.34M/44.7M [00:00<00:00, 41.0MB/s]
67%|######6 | 29.8M/44.7M [00:00<00:00, 122MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 124MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
83%|########3 | 37.2M/44.7M [00:00<00:00, 198MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 186MB/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 356ab0551..43d9b260b 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -370,11 +370,6 @@ Run the corresponding model on tensorflow
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 2.941 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 ea7c370ba..1dddb1509 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
@@ -5,15 +5,15 @@
Computation times
=================
-**05:17.383** total execution time for **how_to_compile_models** files:
+**05:15.477** total execution time for **how_to_compile_models** files:
-- **01:05.658**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:02.941**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:55.811**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:30.013**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:25.255**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.744**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:20.696**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:19.257**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:13.417**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.593**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:06.918**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **00:59.815**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:55.491**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:31.087**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:25.177**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.531**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:20.848**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:18.629**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.297**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.684**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
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 7c9ef5583..afce61c18 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
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6744 15.6781 15.7798 15.5871 0.0616
+ 15.9735 15.9725 16.1387 15.8400 0.0920
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 eb22e1d94..33537b230 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
@@ -108,7 +108,7 @@ 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 | 4.06M/170M [00:00<00:04, 42.3MB/s]
6%|5 | 9.72M/170M [00:00<00:03, 52.3MB/s]
9%|8 | 14.7M/170M [00:00<00:03, 49.2MB/s]
12%|#1 | 19.6M/170M [00:00<00:03, 49.5MB/s]
15%|#4 | 25.1M/170M [00:00<00:02, 52.3MB/s]
18%|#7 | 30.2M/170M [00:00<00:02, 52.9MB/s]
21%|## | 35.3M/170M [00:00<00:02, 49.6MB/s]
24%|##4 | 41.1M/170M [00:00<00:02, 52.3MB/s]
27%|##7 | 46.1M/170M [00:00<00:02, 45.5MB/s]
30%|##9 | 50.6M/170M [00:01<00:03, 38.2MB/s]
33%|###2 | 55.7M/170M [00:01<00:02, 41.8MB/s]
35%|###5 | 59.9M/170M [00:01<00:02, 41.9MB/s]
38%|###7 | 64.1M/170M [00:01<00:02, 40.2MB/s]
40%|#### | 68.1M/170M [00:01<00:03, 34.5MB/s]
42%|####2 | 71.6M/170M [00:02<00:05, 20.4MB/s]
44%|####3 | 74.3M/170M [00:02<00:04, 21.2MB/s]
47%|####6 | 79.7M/170M [00:02<00:03, 27.9MB/
s]
49%|####8 | 83.2M/170M [00:02<00:03, 29.7MB/s]
51%|#####1 | 86.8M/170M [00:02<00:02, 31.2MB/s]
53%|#####3 | 90.7M/170M [00:02<00:02, 33.6MB/s]
56%|#####5 | 95.0M/170M [00:02<00:02, 36.5MB/s]
58%|#####8 | 99.3M/170M [00:02<00:01, 38.8MB/s]
61%|######1 | 104M/170M [00:02<00:01, 41.9MB/s]
64%|######3 | 108M/170M [00:02<00:01, 42.8MB/s]
66%|######6 | 113M/170M [00:03<00:01, 35.7MB/s]
69%|######8 | 117M/170M [00:03<00:01, 37.0MB/s]
71%|#######1 | 121M/170M [00:03<00:01, 38.9MB/s]
74%|#######3 | 125M/170M [00:03<00:01, 40.2MB/s]
77%|#######6 | 130M/170M [00:03<00:00, 44.3MB/s]
80%|#######9 | 135M/170M [00:03<00:00, 46.4MB/s]
83%|########2 | 141M/170M [00:03<00:00, 49.2MB/s]
86%|########5 | 146M/170M [00:03<00:00, 50.3MB/s]
89%|########8 | 151M/170M [00:04<00:00, 44.8MB/s]
92%|#########1| 156M/170M [00:04<00:00, 46.2MB/s]
94%|#########4| 160M/170M [00:04<00:00, 41.9MB/s
]
97%|#########6| 164M/170M [00:04<00:00, 42.6MB/s]
99%|#########9| 169M/170M [00:04<00:00, 40.8MB/s]
100%|##########| 170M/170M [00:04<00:00, 39.7MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
6%|5 | 9.83M/170M [00:00<00:01, 103MB/s]
12%|#1 | 19.7M/170M [00:00<00:01, 92.6MB/s]
17%|#7 | 28.9M/170M [00:00<00:01, 94.6MB/s]
23%|##2 | 38.8M/170M [00:00<00:01, 97.8MB/s]
28%|##8 | 48.1M/170M [00:00<00:01, 86.4MB/s]
33%|###3 | 56.6M/170M [00:00<00:01, 84.6MB/s]
39%|###8 | 65.8M/170M [00:00<00:01, 88.1MB/s]
44%|####4 | 74.8M/170M [00:00<00:01, 90.0MB/s]
49%|####9 | 83.5M/170M [00:00<00:01, 83.4MB/s]
55%|#####5 | 93.8M/170M [00:01<00:00, 89.8MB/s]
60%|###### | 103M/170M [00:01<00:00, 90.1MB/s]
65%|######5 | 111M/170M [00:01<00:00, 84.9MB/s]
71%|#######1 | 121M/170M [00:01<00:00, 90.6MB/s]
77%|#######6 | 131M/170M [00:01<00:00, 93.1MB/s]
83%|########3 | 142M/170M [00:01<00:00, 99.3MB/s]
89%|########9 | 152M/170M [00:01<00:00, 101MB/s]
95%|#########5| 162M/170M [00:01<00:00, 90.9MB/s]
100%|##########| 170M/170M [00:01<00:00, 89.6MB/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').
@@ -253,7 +253,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 6.931 seconds)
+ **Total running time of the script:** ( 3 minutes 4.101 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 dc929c286..2dbff2f83 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ 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]
100%|##########| 13.6M/13.6M [00:00<00:00, 178MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 180MB/s]
@@ -344,7 +344,7 @@ 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)
- 90.2875 90.1954 91.3833 90.0761 0.2433
+ 90.3897 90.2330 92.7423 89.9795 0.3807
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.243 seconds)
+ **Total running time of the script:** ( 1 minutes 4.622 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 09b4a6f69..cd0bd55dc 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
@@ -351,7 +351,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.4826 120.3870 125.9365 119.0509 0.8410
+ 119.5120 119.4274 121.5809 118.4995 0.4991
@@ -385,7 +385,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 6.508 seconds)
+ **Total running time of the script:** ( 1 minutes 56.016 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 e80c84164..fb8f2f7c7 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 25.587 seconds)
+ **Total running time of the script:** ( 1 minutes 10.968 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 0057af4ad..f7230dd04 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
@@ -137,7 +137,7 @@ 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]
0%| | 123/132723 [00:00<01:52, 1174.93KB/s]
5%|4 | 6216/132723 [00:00<00:03, 35658.17KB/s]
11%|# | 14185/132723 [00:00<00:02, 55550.64KB/s]
17%|#6 | 22359/132723 [00:00<00:01, 65821.34KB/s]
23%|##3 | 30632/132723 [00:00<00:01, 71890.82KB/s]
29%|##9 | 38918/132723 [00:00<00:01, 75606.55KB/s]
35%|###5 | 47046/132723 [00:00<00:01, 77452.15KB/s]
42%|####1 | 55277/132723 [00:00<00:00, 78986.27KB/s]
48%|####7 | 63446/132723 [00:00<00:00, 79829.24KB/s]
54%|#####3 | 71669/132723 [00:01<00:00, 80565.82KB/s]
60%|###### | 79920/132723 [00:01<00:00, 81156.58KB/s]
66%|######6 | 88131/132723 [00:01<00:00, 81443.10KB/s]
73%|#######2 | 96329/132723 [00:01<00:00, 81604.37KB/s]
79%|#######8 | 104550/132723 [00:01<00:00, 81785.63KB/s]
85%|########4 | 112730/132723 [00:01<00:00, 81765.43KB/s]
91%|#########1|
121031/132723 [00:01<00:00, 82136.82KB/s]
97%|#########7| 129290/132723 [00:01<00:00, 82271.61KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75977.13KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3469/132723 [00:00<00:03, 34420.94KB/s]
7%|6 | 8811/132723 [00:00<00:02, 45556.38KB/s]
13%|#2 | 16679/132723 [00:00<00:01, 60652.65KB/s]
19%|#8 | 24681/132723 [00:00<00:01, 68288.44KB/s]
25%|##4 | 32729/132723 [00:00<00:01, 72675.72KB/s]
31%|### | 40742/132723 [00:00<00:01, 75206.24KB/s]
37%|###6 | 48808/132723 [00:00<00:01, 76987.35KB/s]
43%|####2 | 56841/132723 [00:00<00:00, 78048.74KB/s]
49%|####8 | 64647/132723 [00:00<00:00, 77763.41KB/s]
55%|#####4 | 72448/132723 [00:01<00:00, 77835.59KB/s]
60%|###### | 80248/132723 [00:01<00:00, 77876.25KB/s]
66%|######6 | 88037/132723 [00:01<00:00, 77740.81KB/s]
72%|#######2 | 95812/132723 [00:01<00:00, 77595.04KB/s]
78%|#######8 | 103608/132723 [00:01<00:00, 77701.18KB/s]
84%|########3 | 111379/132723 [00:01<00:00, 77457.54KB/s]
90%|########9
| 119126/132723 [00:01<00:00, 77329.54KB/s]
96%|#########5| 126864/132723 [00:01<00:00, 77340.81KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74499.40KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 22.499 seconds)
+ **Total running time of the script:** ( 2 minutes 22.450 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 99a5a2839..6d9425c0c 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
@@ -5,13 +5,13 @@
Computation times
=================
-**10:55.932** total execution time for **how_to_deploy_models** files:
+**10:27.704** total execution time for **how_to_deploy_models** files:
-- **03:06.931**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:22.499**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **02:06.508**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:25.587**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:04.243**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:27.947**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.029**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.188**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:04.101**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:22.450**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:56.016**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:10.968**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:04.622**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.896**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.451**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.202**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
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 f95f1da23..34bc87b99 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
@@ -423,7 +423,7 @@ 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.zip9a4dd0be-f3aa-40f1-bbd1-ffd3329b9539 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb1c37f6d-754c-4b34-aca9-d8ed44396371 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 51602d4d2..9968ab331 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
@@ -5,9 +5,9 @@
Computation times
=================
-**00:38.152** total execution time for **how_to_extend_tvm** files:
+**00:37.957** total execution time for **how_to_extend_tvm** files:
-- **00:34.636**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.258**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.061**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.198**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.493**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.229**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.040**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.194**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
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 a2f9cbd1b..e6af86a44 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
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6019us [6019us] (45.46%; 45.46%)
- FoldScaleAxis: 7221us [2us] (54.54%; 54.54%)
- FoldConstant: 7219us [1511us] (54.52%; 99.97%)
- InferType: 5708us [5708us] (43.11%; 79.07%)
+ InferType: 5847us [5847us] (44.94%; 44.94%)
+ FoldScaleAxis: 7163us [2us] (55.06%; 55.06%)
+ FoldConstant: 7161us [1488us] (55.04%; 99.97%)
+ InferType: 5673us [5673us] (43.61%; 79.22%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 5774us [5774us] (44.49%; 44.49%)
- FoldScaleAxis: 7205us [2us] (55.51%; 55.51%)
- FoldConstant: 7203us [1479us] (55.50%; 99.98%)
- InferType: 5724us [5724us] (44.10%; 79.46%)
+ InferType: 5683us [5683us] (44.20%; 44.20%)
+ FoldScaleAxis: 7173us [2us] (55.80%; 55.80%)
+ FoldConstant: 7171us [1510us] (55.78%; 99.98%)
+ InferType: 5661us [5661us] (44.04%; 78.94%)
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 e8a0cc43b..0b2fcf796 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
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 44.075864 ms
+ Convolution: 54.134968 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 e9abab6fe..ae4f18a19 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
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.736506 ms
+ conv2d with tensor core: 7.091136 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 19a4162a2..bd22967c6 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018356
- Baseline: 3.414940
+ Numpy running time: 0.018117
+ Baseline: 3.197863
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.301714
+ Opt1: 0.302272
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.336810
+ Opt2: 0.341488
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116738
+ Opt3: 0.120279
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110333
+ Opt4: 0.111055
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111412
+ Opt5: 0.111010
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145097
+ Opt6: 0.144610
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 5ecdbdfcf..785453133 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:35.069** total execution time for **how_to_optimize_operators** files:
+**00:34.438** total execution time for **how_to_optimize_operators** files:
-- **00:32.405**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.447**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.216**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:31.826**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.414**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.197**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
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 b20b995f9..1c6530c20 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
@@ -5,11 +5,11 @@
Computation times
=================
-**04:51.474** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:16.560**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:20.012**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.421**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:17.102**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.869**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.510**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:55.482** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:20.906**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:19.998**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.306**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:17.326**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.590**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.355**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
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 961c7f153..2970f2f48 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
@@ -222,240 +222,689 @@ 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, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*3136)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*576)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 112), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 112), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 224), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 224), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 336), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 336), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 448), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 448), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 560), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 560), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 672), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 672), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 896), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 896), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1120), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1120), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1232), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1232), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1344), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1344), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1456), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1456), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1680), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1680), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1792), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1792), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1904), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1904), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1560)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2128), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2128), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2128), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2240), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2240), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2240), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2352), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2464), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2464), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2464), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2576), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2576), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2576), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2688)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2688), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2688), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2688), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2800)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2800), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2800), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2800), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2912)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2912), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2912), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2912), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3024)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2344)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3136), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3248)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3248), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3248), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3248), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3360)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3360), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3360), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3360), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3472)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3472), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3472), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3472), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3584)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3584), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3584), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3584), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3696)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3696), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3696), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3696), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3808)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3808), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3808), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3808), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3920), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3920), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3920), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[(threadIdx.x_2*4)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 448), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 449)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 449), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 450)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 451)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 448), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 896), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 897)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 898)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 898), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 899)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 896), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 1344)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 32256)]
- kernel.shared_1[((threadIdx.x_2*4) + 1345)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1345), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 32256)]
- kernel.shared_1[((threadIdx.x_2*4) + 1346)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1346), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 32256)]
- kernel.shared_1[((threadIdx.x_2*4) + 1347)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 32256)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 1792)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1792), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1793)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1793), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1794)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1795)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 1792), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2240), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2241)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2242)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2242), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2243)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 2240), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 2688)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*4) + 2689)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2689), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*4) + 2690)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2690), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*4) + 2691)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 64512)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3136), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3137)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3137), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3138)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3139)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 3136), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 3584)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3584), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3585)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3586)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3586), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3587)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 3584), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 4032)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 96768)]
- kernel.shared_1[((threadIdx.x_2*4) + 4033)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4033), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 96768)]
- kernel.shared_1[((threadIdx.x_2*4) + 4034)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4034), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 96768)]
- kernel.shared_1[((threadIdx.x_2*4) + 4035)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 96768)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 4480)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4480), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4481)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4481), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4482)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4483)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 4480), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 4928)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4928), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4929)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4930)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4930), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4931)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 4928), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 5376)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*4) + 5377)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5377), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*4) + 5378)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5378), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*4) + 5379)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 129024)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5824)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5824), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5825)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5825), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5826)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- }
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5827)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 5824), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 32) {
- let cse_var_11: int32 = (ff.outer.inner*7)
- let cse_var_10: int32 = (cse_var_11 + 6)
- let cse_var_9: int32 = (cse_var_11 + 5)
- let cse_var_8: int32 = (cse_var_11 + 4)
- let cse_var_7: int32 = (cse_var_11 + 3)
- let cse_var_6: int32 = (cse_var_11 + 2)
- let cse_var_5: int32 = (cse_var_11 + 1)
- {
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[(((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- }
- }
- }
- }
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 9)*7)) + (floormod(blockIdx.x, 7)*7 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 192), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 312), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 408), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 424), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 440), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 456), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 472), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 488), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 520), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 536), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 552), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 568), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
- }
+ compute[(((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
}
}
@@ -507,7 +956,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.336 ms
+ Execution time of this operator: 0.260 ms
@@ -552,36 +1001,36 @@ 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=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=16)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=7)
+ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, 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=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_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=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=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=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
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])
@@ -598,16 +1047,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=4)
+ 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=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
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=112)
+ 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", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -625,10 +1074,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[6144];
+ 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[7];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -636,151 +1085,599 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1560)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2128) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2240) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2464) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2576)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2576) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2688)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2688) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2800)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2800) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2912)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2912) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3024)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2344)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3248)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3248) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3360)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3360) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3472)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3472) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3584)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3584) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3696)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3696) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3808)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3808) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[(((int)threadIdx.x) * 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 1) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 2) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 449)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 450)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 451)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 448) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 897)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 898)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 899)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 896) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1344)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1345)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1346)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1347)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1793)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1794)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1795)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 1792) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2241)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2242)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2243)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 2240) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2688)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2689)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2690)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2691)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3137)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3138)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3139)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 3136) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3584)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3585)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3586)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3587)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 3584) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4032)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4033)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4034)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4035)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4480)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4481)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4482)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4483)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 4480) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4928)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4929)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4930)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4931)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 4928) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 5376)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 4) + 5377)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 4) + 5378)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 4) + 5379)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 129024)];
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5824)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- }
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5825)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- }
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5826)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- }
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5827)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 5824) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 32; ++rc_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- }
- }
- }
- }
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : [...]
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] [...]
+ if (((int)threadIdx.x) < 24) {
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= ((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) + 3) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : [...]
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
}
@@ -838,7 +1735,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 16.560 seconds)
+ **Total running time of the script:** ( 2 minutes 20.906 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 f6f396f19..45ee3108d 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
@@ -614,7 +614,7 @@ 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)
- 10.0346 10.0229 10.0847 9.9962 0.0371
+ 9.7771 9.7825 9.8053 9.7436 0.0255
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 91f2cfb6c..e52f75d20 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
@@ -633,7 +633,7 @@ 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)
- 760.1481 761.7492 765.0381 753.6569 4.7823
+ 765.3085 765.3539 767.8644 762.7072 2.1057
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.012 seconds)
+ **Total running time of the script:** ( 1 minutes 19.998 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 f287e9f10..81bada5c7 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
@@ -362,74 +362,407 @@ 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_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (i.inner.init*16)
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ let cse_var_2: int32 = (nb_j.inner*16)
+ let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
{
- compute_5: Buffer(compute_4, float32, [1024], [])[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
- }
- }
- 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, 64) {
- let cse_var_21: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_20: int32 = (i.inner*16)
- let cse_var_19: int32 = (elem_idx*16)
- let cse_var_18: int32 = (cse_var_20 + 10)
- let cse_var_17: int32 = (cse_var_20 + 11)
- let cse_var_16: int32 = (cse_var_20 + 12)
- let cse_var_15: int32 = (cse_var_20 + 13)
- let cse_var_14: int32 = (cse_var_20 + 14)
- let cse_var_13: int32 = (cse_var_20 + 15)
- let cse_var_12: int32 = (cse_var_20 + 2)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 4)
- let cse_var_9: int32 = (cse_var_20 + 5)
- let cse_var_8: int32 = (cse_var_20 + 6)
- let cse_var_7: int32 = (cse_var_20 + 7)
- let cse_var_6: int32 = (cse_var_20 + 8)
- let cse_var_5: int32 = (cse_var_20 + 9)
- let cse_var_4: int32 = (cse_var_20 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.inner*256))
- {
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_19)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5: Buffer(compute_4, float32, [256], [])[cse_var_2] = 0f32
+ compute_5[(cse_var_2 + 1)] = 0f32
+ compute_5[(cse_var_2 + 2)] = 0f32
+ compute_5[(cse_var_2 + 3)] = 0f32
+ compute_5[(cse_var_2 + 4)] = 0f32
+ compute_5[(cse_var_2 + 5)] = 0f32
+ compute_5[(cse_var_2 + 6)] = 0f32
+ compute_5[(cse_var_2 + 7)] = 0f32
+ compute_5[(cse_var_2 + 8)] = 0f32
+ compute_5[(cse_var_2 + 9)] = 0f32
+ compute_5[(cse_var_2 + 10)] = 0f32
+ compute_5[(cse_var_2 + 11)] = 0f32
+ compute_5[(cse_var_2 + 12)] = 0f32
+ compute_5[(cse_var_2 + 13)] = 0f32
+ compute_5[(cse_var_2 + 14)] = 0f32
+ compute_5[(cse_var_2 + 15)] = 0f32
+ compute_5[(cse_var_2 + 32)] = 0f32
+ compute_5[(cse_var_2 + 33)] = 0f32
+ compute_5[(cse_var_2 + 34)] = 0f32
+ compute_5[(cse_var_2 + 35)] = 0f32
+ compute_5[(cse_var_2 + 36)] = 0f32
+ compute_5[(cse_var_2 + 37)] = 0f32
+ compute_5[(cse_var_2 + 38)] = 0f32
+ compute_5[(cse_var_2 + 39)] = 0f32
+ compute_5[(cse_var_2 + 40)] = 0f32
+ compute_5[(cse_var_2 + 41)] = 0f32
+ compute_5[(cse_var_2 + 42)] = 0f32
+ compute_5[(cse_var_2 + 43)] = 0f32
+ compute_5[(cse_var_2 + 44)] = 0f32
+ compute_5[(cse_var_2 + 45)] = 0f32
+ compute_5[(cse_var_2 + 46)] = 0f32
+ compute_5[(cse_var_2 + 47)] = 0f32
+ compute_5[(cse_var_2 + 64)] = 0f32
+ compute_5[(cse_var_2 + 65)] = 0f32
+ compute_5[(cse_var_2 + 66)] = 0f32
+ compute_5[(cse_var_2 + 67)] = 0f32
+ compute_5[(cse_var_2 + 68)] = 0f32
+ compute_5[(cse_var_2 + 69)] = 0f32
+ compute_5[(cse_var_2 + 70)] = 0f32
+ compute_5[(cse_var_2 + 71)] = 0f32
+ compute_5[(cse_var_2 + 72)] = 0f32
+ compute_5[(cse_var_2 + 73)] = 0f32
+ compute_5[(cse_var_2 + 74)] = 0f32
+ compute_5[(cse_var_2 + 75)] = 0f32
+ compute_5[(cse_var_2 + 76)] = 0f32
+ compute_5[(cse_var_2 + 77)] = 0f32
+ compute_5[(cse_var_2 + 78)] = 0f32
+ compute_5[(cse_var_2 + 79)] = 0f32
+ compute_5[(cse_var_2 + 96)] = 0f32
+ compute_5[(cse_var_2 + 97)] = 0f32
+ compute_5[(cse_var_2 + 98)] = 0f32
+ compute_5[(cse_var_2 + 99)] = 0f32
+ compute_5[(cse_var_2 + 100)] = 0f32
+ compute_5[(cse_var_2 + 101)] = 0f32
+ compute_5[(cse_var_2 + 102)] = 0f32
+ compute_5[(cse_var_2 + 103)] = 0f32
+ compute_5[(cse_var_2 + 104)] = 0f32
+ compute_5[(cse_var_2 + 105)] = 0f32
+ compute_5[(cse_var_2 + 106)] = 0f32
+ compute_5[(cse_var_2 + 107)] = 0f32
+ compute_5[(cse_var_2 + 108)] = 0f32
+ compute_5[(cse_var_2 + 109)] = 0f32
+ compute_5[(cse_var_2 + 110)] = 0f32
+ compute_5[(cse_var_2 + 111)] = 0f32
+ compute_5[(cse_var_2 + 128)] = 0f32
+ compute_5[(cse_var_2 + 129)] = 0f32
+ compute_5[(cse_var_2 + 130)] = 0f32
+ compute_5[(cse_var_2 + 131)] = 0f32
+ compute_5[(cse_var_2 + 132)] = 0f32
+ compute_5[(cse_var_2 + 133)] = 0f32
+ compute_5[(cse_var_2 + 134)] = 0f32
+ compute_5[(cse_var_2 + 135)] = 0f32
+ compute_5[(cse_var_2 + 136)] = 0f32
+ compute_5[(cse_var_2 + 137)] = 0f32
+ compute_5[(cse_var_2 + 138)] = 0f32
+ compute_5[(cse_var_2 + 139)] = 0f32
+ compute_5[(cse_var_2 + 140)] = 0f32
+ compute_5[(cse_var_2 + 141)] = 0f32
+ compute_5[(cse_var_2 + 142)] = 0f32
+ compute_5[(cse_var_2 + 143)] = 0f32
+ compute_5[(cse_var_2 + 160)] = 0f32
+ compute_5[(cse_var_2 + 161)] = 0f32
+ compute_5[(cse_var_2 + 162)] = 0f32
+ compute_5[(cse_var_2 + 163)] = 0f32
+ compute_5[(cse_var_2 + 164)] = 0f32
+ compute_5[(cse_var_2 + 165)] = 0f32
+ compute_5[(cse_var_2 + 166)] = 0f32
+ compute_5[(cse_var_2 + 167)] = 0f32
+ compute_5[(cse_var_2 + 168)] = 0f32
+ compute_5[(cse_var_2 + 169)] = 0f32
+ compute_5[(cse_var_2 + 170)] = 0f32
+ compute_5[(cse_var_2 + 171)] = 0f32
+ compute_5[(cse_var_2 + 172)] = 0f32
+ compute_5[(cse_var_2 + 173)] = 0f32
+ compute_5[(cse_var_2 + 174)] = 0f32
+ compute_5[(cse_var_2 + 175)] = 0f32
+ compute_5[(cse_var_2 + 192)] = 0f32
+ compute_5[(cse_var_2 + 193)] = 0f32
+ compute_5[(cse_var_2 + 194)] = 0f32
+ compute_5[(cse_var_2 + 195)] = 0f32
+ compute_5[(cse_var_2 + 196)] = 0f32
+ compute_5[(cse_var_2 + 197)] = 0f32
+ compute_5[(cse_var_2 + 198)] = 0f32
+ compute_5[(cse_var_2 + 199)] = 0f32
+ compute_5[(cse_var_2 + 200)] = 0f32
+ compute_5[(cse_var_2 + 201)] = 0f32
+ compute_5[(cse_var_2 + 202)] = 0f32
+ compute_5[(cse_var_2 + 203)] = 0f32
+ compute_5[(cse_var_2 + 204)] = 0f32
+ compute_5[(cse_var_2 + 205)] = 0f32
+ compute_5[(cse_var_2 + 206)] = 0f32
+ compute_5[(cse_var_2 + 207)] = 0f32
+ compute_5[(cse_var_2 + 224)] = 0f32
+ compute_5[(cse_var_2 + 225)] = 0f32
+ compute_5[(cse_var_2 + 226)] = 0f32
+ compute_5[(cse_var_2 + 227)] = 0f32
+ compute_5[(cse_var_2 + 228)] = 0f32
+ compute_5[(cse_var_2 + 229)] = 0f32
+ compute_5[(cse_var_2 + 230)] = 0f32
+ compute_5[(cse_var_2 + 231)] = 0f32
+ compute_5[(cse_var_2 + 232)] = 0f32
+ compute_5[(cse_var_2 + 233)] = 0f32
+ compute_5[(cse_var_2 + 234)] = 0f32
+ compute_5[(cse_var_2 + 235)] = 0f32
+ compute_5[(cse_var_2 + 236)] = 0f32
+ compute_5[(cse_var_2 + 237)] = 0f32
+ compute_5[(cse_var_2 + 238)] = 0f32
+ compute_5[(cse_var_2 + 239)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ let cse_var_131: int32 = (cse_var_2 + 143)
+ let cse_var_130: int32 = (cse_var_2 + 15)
+ let cse_var_129: int32 = (cse_var_2 + 160)
+ let cse_var_128: int32 = (cse_var_2 + 161)
+ let cse_var_127: int32 = (cse_var_2 + 162)
+ let cse_var_126: int32 = (cse_var_2 + 163)
+ let cse_var_125: int32 = (cse_var_2 + 164)
+ let cse_var_124: int32 = (cse_var_2 + 165)
+ let cse_var_123: int32 = (cse_var_2 + 166)
+ let cse_var_122: int32 = (cse_var_2 + 167)
+ let cse_var_121: int32 = (cse_var_2 + 168)
+ let cse_var_120: int32 = (cse_var_2 + 169)
+ let cse_var_119: int32 = (cse_var_2 + 170)
+ let cse_var_118: int32 = (cse_var_2 + 171)
+ let cse_var_117: int32 = (cse_var_2 + 172)
+ let cse_var_116: int32 = (cse_var_2 + 1)
+ let cse_var_115: int32 = (cse_var_2 + 174)
+ let cse_var_114: int32 = (cse_var_2 + 175)
+ let cse_var_113: int32 = (cse_var_2 + 192)
+ let cse_var_112: int32 = (cse_var_2 + 193)
+ let cse_var_111: int32 = (cse_var_2 + 194)
+ let cse_var_110: int32 = (cse_var_2 + 195)
+ let cse_var_109: int32 = (cse_var_2 + 196)
+ let cse_var_108: int32 = (cse_var_2 + 197)
+ let cse_var_107: int32 = (cse_var_2 + 198)
+ let cse_var_106: int32 = (cse_var_2 + 199)
+ let cse_var_105: int32 = (cse_var_2 + 2)
+ let cse_var_104: int32 = (cse_var_2 + 200)
+ let cse_var_103: int32 = (cse_var_2 + 201)
+ let cse_var_102: int32 = (cse_var_2 + 202)
+ let cse_var_101: int32 = (cse_var_2 + 203)
+ let cse_var_100: int32 = (cse_var_2 + 173)
+ let cse_var_99: int32 = (cse_var_2 + 10)
+ let cse_var_98: int32 = (cse_var_2 + 100)
+ let cse_var_97: int32 = (cse_var_2 + 101)
+ let cse_var_96: int32 = (cse_var_2 + 102)
+ let cse_var_95: int32 = (cse_var_2 + 103)
+ let cse_var_94: int32 = (cse_var_2 + 104)
+ let cse_var_93: int32 = (cse_var_2 + 105)
+ let cse_var_92: int32 = (cse_var_2 + 106)
+ let cse_var_91: int32 = (cse_var_2 + 107)
+ let cse_var_90: int32 = (cse_var_2 + 108)
+ let cse_var_89: int32 = (cse_var_2 + 109)
+ let cse_var_88: int32 = (cse_var_2 + 11)
+ let cse_var_87: int32 = (cse_var_2 + 110)
+ let cse_var_86: int32 = (cse_var_2 + 111)
+ let cse_var_85: int32 = (cse_var_2 + 12)
+ let cse_var_84: int32 = (cse_var_2 + 142)
+ let cse_var_83: int32 = (cse_var_2 + 129)
+ let cse_var_82: int32 = (cse_var_2 + 13)
+ let cse_var_81: int32 = (cse_var_2 + 130)
+ let cse_var_80: int32 = (cse_var_2 + 131)
+ let cse_var_79: int32 = (cse_var_2 + 132)
+ let cse_var_78: int32 = (cse_var_2 + 133)
+ let cse_var_77: int32 = (cse_var_2 + 134)
+ let cse_var_76: int32 = (cse_var_2 + 135)
+ let cse_var_75: int32 = (cse_var_2 + 136)
+ let cse_var_74: int32 = (cse_var_2 + 137)
+ let cse_var_73: int32 = (cse_var_2 + 138)
+ let cse_var_72: int32 = (cse_var_2 + 139)
+ let cse_var_71: int32 = (cse_var_2 + 14)
+ let cse_var_70: int32 = (cse_var_2 + 140)
+ let cse_var_69: int32 = (cse_var_2 + 141)
+ let cse_var_68: int32 = (cse_var_2 + 128)
+ let cse_var_67: int32 = (cse_var_2 + 43)
+ let cse_var_66: int32 = (cse_var_2 + 44)
+ let cse_var_65: int32 = (cse_var_2 + 45)
+ let cse_var_64: int32 = (cse_var_2 + 46)
+ let cse_var_63: int32 = (cse_var_2 + 47)
+ let cse_var_62: int32 = (cse_var_2 + 5)
+ let cse_var_61: int32 = (cse_var_2 + 6)
+ let cse_var_60: int32 = (cse_var_2 + 64)
+ let cse_var_59: int32 = (cse_var_2 + 65)
+ let cse_var_58: int32 = (cse_var_2 + 66)
+ let cse_var_57: int32 = (cse_var_2 + 67)
+ let cse_var_56: int32 = (cse_var_2 + 68)
+ let cse_var_55: int32 = (cse_var_2 + 69)
+ let cse_var_54: int32 = (cse_var_2 + 7)
+ let cse_var_53: int32 = (cse_var_2 + 70)
+ let cse_var_52: int32 = (cse_var_2 + 42)
+ let cse_var_51: int32 = (cse_var_2 + 72)
+ let cse_var_50: int32 = (cse_var_2 + 73)
+ let cse_var_49: int32 = (cse_var_2 + 74)
+ let cse_var_48: int32 = (cse_var_2 + 75)
+ let cse_var_47: int32 = (cse_var_2 + 76)
+ let cse_var_46: int32 = (cse_var_2 + 77)
+ let cse_var_45: int32 = (cse_var_2 + 78)
+ let cse_var_44: int32 = (cse_var_2 + 79)
+ let cse_var_43: int32 = (cse_var_2 + 8)
+ let cse_var_42: int32 = (cse_var_2 + 9)
+ let cse_var_41: int32 = (cse_var_2 + 96)
+ let cse_var_40: int32 = (cse_var_2 + 97)
+ let cse_var_39: int32 = (cse_var_2 + 98)
+ let cse_var_38: int32 = (cse_var_2 + 99)
+ let cse_var_37: int32 = (elem_idx*16)
+ let cse_var_36: int32 = (cse_var_2 + 71)
+ let cse_var_35: int32 = (cse_var_2 + 204)
+ let cse_var_34: int32 = (cse_var_2 + 206)
+ let cse_var_33: int32 = (cse_var_2 + 207)
+ let cse_var_32: int32 = (cse_var_2 + 224)
+ let cse_var_31: int32 = (cse_var_2 + 225)
+ let cse_var_30: int32 = (cse_var_2 + 226)
+ let cse_var_29: int32 = (cse_var_2 + 227)
+ let cse_var_28: int32 = (cse_var_2 + 228)
+ let cse_var_27: int32 = (cse_var_2 + 229)
+ let cse_var_26: int32 = (cse_var_2 + 230)
+ let cse_var_25: int32 = (cse_var_2 + 231)
+ let cse_var_24: int32 = (cse_var_2 + 232)
+ let cse_var_23: int32 = (cse_var_2 + 233)
+ let cse_var_22: int32 = (cse_var_2 + 234)
+ let cse_var_21: int32 = (cse_var_2 + 235)
+ let cse_var_20: int32 = (cse_var_2 + 236)
+ let cse_var_19: int32 = (cse_var_2 + 205)
+ let cse_var_18: int32 = (cse_var_2 + 40)
+ let cse_var_17: int32 = (cse_var_2 + 4)
+ let cse_var_16: int32 = (cse_var_2 + 39)
+ let cse_var_15: int32 = (cse_var_2 + 38)
+ let cse_var_14: int32 = (cse_var_2 + 37)
+ let cse_var_13: int32 = (cse_var_2 + 36)
+ let cse_var_12: int32 = (cse_var_2 + 35)
+ let cse_var_11: int32 = (cse_var_2 + 34)
+ let cse_var_10: int32 = (cse_var_2 + 33)
+ let cse_var_9: int32 = (cse_var_2 + 32)
+ let cse_var_8: int32 = (cse_var_2 + 3)
+ let cse_var_7: int32 = (cse_var_2 + 239)
+ let cse_var_6: int32 = (cse_var_2 + 238)
+ let cse_var_5: int32 = (cse_var_2 + 41)
+ let cse_var_4: int32 = (cse_var_2 + 237)
+ let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*2048)
+ {
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_130] = (compute_5[cse_var_130] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_131] = (compute_5[cse_var_131] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_22, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_22, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_132, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -483,7 +816,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.842 ms
+ Execution time of this operator: 2.721 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 09ea35ef1..464f14fc4 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.335** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.648** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.459**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.224**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.221**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.208**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:43.755**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.235**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.218**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
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 293187397..53bc35489 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
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 104.05/104.05 result: MeasureResult(costs=(0.0022248586250000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5778279304504395, timestamp=1651278117.4312086) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 43.38/43.38 result: MeasureResult(costs=(0.005336062894736842,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.565807819366455, timestamp=1651281447.9343586) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/43.38 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
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f015c92afa2
+ 12: 0x00007f2abf079fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 142.22/142.22 result: MeasureResult(costs=(0.001627716564516129,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.128873348236084, timestamp=1651278143.517314) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 144.39/144.39 result: MeasureResult(costs=(0.00160325892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4100971221923828, timestamp=1651281474.2659922) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.001980
+ Time cost of this operator: 0.001989
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 2a50d40c7..012e35094 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
@@ -292,10 +292,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.6 98.738 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.967 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.934 0.294 (1, 1, 10, 10, 3) 1 1
- Total_time - 317.607 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.1 98.716 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.138 0.989 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 0.295 (1, 1, 10, 10, 3) 1 1
+ Total_time - 317.174 - - - -
@@ -357,10 +357,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.6 96.886 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.702 2.02 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 1.094 (1, 1, 10, 10, 3) 1 1
- Total_time - 84.223 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.05 96.807 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.104 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.089 (1, 1, 10, 10, 3) 1 1
+ Total_time - 82.691 - - - -
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 3bbd14ffb..0c49b87cf 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.341** total execution time for **how_to_work_with_microtvm** files:
+**00:43.818** total execution time for **how_to_work_with_microtvm** files:
-- **00:40.252**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.481**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.207**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.203**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.199**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:39.780**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.439**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.204**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:00.198**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.197**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
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 7aab35689..943036aca 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:08.938** total execution time for **how_to_work_with_relay** files:
+**00:08.903** total execution time for **how_to_work_with_relay** files:
-- **00:06.970**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.744**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.223**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:07.037**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.660**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.207**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
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 f7c9b09ba..dcd84b0aa 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
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.652** total execution time for **how_to_work_with_schedules** files:
+**00:05.706** total execution time for **how_to_work_with_schedules** files:
-- **00:02.075**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.149**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.723**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.704**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.306**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.243**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.240**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.213**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.112**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.121**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.735**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.725**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.310**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.244**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.236**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.224**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
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 2974e7576..f9820a4d4 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -318,7 +318,7 @@ 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/tmp7b7g_5vk/input0.cc'\nsource_filename = \"/tmp/tmp7b7g_5vk/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/tmpw_oz188a/input0.cc'\nsource_filename = \"/tmp/tmpw_oz188a/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 2b2184b44..2046f2442 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.169** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.204** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:19.963**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.206**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.004**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.200**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
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 6dcc4582a..1251a2a41 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ 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 21.20s!
+ resnet18_v1 inference graph built in 21.30s!
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 01d72ed32..ec9b2bfab 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 14.73s!
+ yolov3-tiny inference graph built in 14.86s!
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 53243fa80..de46ebe74 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
@@ -5,7 +5,7 @@
Computation times
=================
-**01:28.387** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.154** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.136**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.250**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.825**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.329**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
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 b03637908..cf818bed7 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.527** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.583** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:02.978**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.549**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:03.047**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.536**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
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 13e4a0914..9883c0c63 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:00.989** total execution time for **topic_vta_tutorials** files:
+**00:01.014** total execution time for **topic_vta_tutorials** files:
-- **00:00.501**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.488**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.514**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.500**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 694e739c5..81535aa68 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.608 ms
+ Execution time of this operator: 96.593 ms
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 25f5cb930..659351a89 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -268,7 +268,7 @@ standard deviation.
.. code-block:: none
- {'mean': 494.3400694800004, 'median': 493.9094355999998, 'std': 1.1932189175639154}
+ {'mean': 491.7812707299992, 'median': 491.7406261499991, 'std': 0.606950351019823}
@@ -482,31 +482,32 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 23.44/ 23.44 GFLOPS | Progress: (4/10) | 5.13 s
[Task 1/25] Current/Best: 14.50/ 23.44 GFLOPS | Progress: (8/10) | 7.60 s
[Task 1/25] Current/Best: 22.82/ 23.56 GFLOPS | Progress: (10/10) | 8.29 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 6.77/ 13.80 GFLOPS | Progress: (4/10) | 2.34 s
[Task 2/25] Current/Best: 17.21/ 17.21 GFLOPS | Progress: (8/10) | 4.05 s
[Task 2/25] Current/Best: 13.61/ 17.21 GFLOPS | Progress: (10/10) | 4.61 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (4/10) | 4.32 s
[Task 3/25] Current/Best: 12.62/ 21.23 GFLOPS | Progress: (8/10) | 6.30 s
[Task 3/25] Current/Best: 24.13/ 24.13 GFLOPS | Progress: (10/10) | 6.99 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 3.46/ 19.08 GFLOPS | Progress: (4/10) | 2.53 s
[Task 4/25] Current/Best: 11.28/ 19.08 GFLOPS | Progress: (8/10) | 4.53 s
[Task 4/25] Current/Best: 11.26/ 19.08 GFLOPS | Progress: (10/10) | 6.36 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 14.47/ 14.47 GFLOPS | Progress: (4/10) | 3.11 s
[Task 5/25] Current/Best: 15.45/ 17.47 GFLOPS | Progress: (8/10) | 5.08 s
[Task 5/25] Current/Best: 13.76/ 17.47 GFLOPS | Progress: (10/10) | 5.87 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 11.03/ 14.94 GFLOPS | Progress: (4/10) | 6.11 s
[Task 6/25] Current/Best: 19.34/ 19.34 GFLOPS | Progress: (8/10) | 8.34 s
[Task 6/25] Current/Best: 6.36/ 19.34 GFLOPS | Progress: (10/10) | 9.73 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 7.84/ 19.00 GFLOPS | Progress: (4/10) | 2.68 s
[Task 7/25] Current/Best: 7.26/ 19.00 GFLOPS | Progress: (8/10) | 4.44 s
[Task 7/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (10/10) | 5.90 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 9.65/ 13.07 GFLOPS | Progress: (4/10) | 7.57 s
[Task 8/25] Current/Best: 12.91/ 13.74 GFLOPS | Progress: (8/10) | 9.64 s
[Task 8/25] Current/Best: 20.11/ 20.11 GFLOPS | Progress: (10/10) | 12.13 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 14.50/ 23.28 GFLOPS | Progress: (4/10) | 6.34 s
[Task 9/25] Current/Best: 14.99/ 23.28 GFLOPS | Progress: (8/10) | 9.37 s
[Task 9/25] Current/Best: 12.19/ 23.28 GFLOPS | Progress: (10/10) | 9.97 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 16.39/ 18.13 GFLOPS | Progress: (4/10) | 3.38 s
[Task 10/25] Current/Best: 19.98/ 19.98 GFLOPS | Progress: (8/10) | 5.05 s
[Task 10/25] Current/Best: 5.83/ 19.98 GFLOPS | Progress: (10/10) | 6.54 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 12.12/ 24.21 GFLOPS | Progress: (4/10) | 2.85 s
[Task 11/25] Current/Best: 16.83/ 24.21 GFLOPS | Progress: (8/10) | 5.56 s
[Task 11/25] Current/Best: 7.23/ 24.21 GFLOPS | Progress: (10/10) | 6.70 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (4/10) | 4.75 s
[Task 12/25] Current/Best: 13.98/ 19.66 GFLOPS | Progress: (8/10) | 6.68 s
[Task 12/25] Current/Best: 17.32/ 19.66 GFLOPS | Progress: (10/10) | 7.57 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 9.48/ 18.14 GFLOPS | Progress: (4/10) | 3.81 s
[Task 13/25] Current/Best: 3.11/ 19.47 GFLOPS | Progress: (8/10) | 6.14 s
[Task 13/25] Current/Best: 9.63/ 19.47 GFLOPS | Progress: (10/10) | 7.03 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 10.01/ 14.25 GFLOPS | Progress: (4/10) | 4.26 s
[Task 14/25] Current/Best: 5.10/ 16.09 GFLOPS | Progress: (8/10) | 10.27 s
[Task 14/25] Current/Best: 16.36/ 16.36 GFLOPS | Progress: (10/10) | 11.10 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 9.28/ 21.43 GFLOPS | Progress: (4/10) | 2.19 s
[Task 15/25] Current/Best: 17.18/ 21.43 GFLOPS | Progress: (8/10) | 7.31 s
[Task 15/25] Current/Best: 15.30/ 21.43 GFLOPS | Progress: (10/10) | 8.53 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (4/10) | 2.69 s
[Task 16/25] Current/Best: 14.67/ 20.12 GFLOPS | Progress: (8/10) | 4.03 s
[Task 16/25] Current/Best: 19.88/ 20.12 GFLOPS | Progress: (10/10) | 4.92 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 23.86/ 23.86 GFLOPS | Progress: (4/10) | 4.40 s
[Task 17/25] Current/Best: 12.31/ 23.86 GFLOPS | Progress: (8/10) | 6.21 s
[Task 17/25] Current/Best: 18.47/ 24.13 GFLOPS | Progress: (10/10) | 7.16 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 11.52/ 12.74 GFLOPS | Progress: (4/10) | 4.55 s
[Task 18/25] Current/Best: 11.94/ 15.86 GFLOPS | Progress: (8/10) | 7.21 s
[Task 18/25] Current/Best: 11.74/ 22.30 GFLOPS | Progress: (10/10) | 8.66 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 19.48/ 22.49 GFLOPS | Progress: (4/10) | 4.01 s
[Task 19/25] Current/Best: 8.63/ 23.03 GFLOPS | Progress: (8/10) | 6.74 s
[Task 19/25] Current/Best: 18.05/ 23.03 GFLOPS | Progress: (10/10) | 8.17 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 9.53/ 16.74 GFLOPS | Progress: (4/10) | 5.32 s
[Task 20/25] Current/Best: 2.69/ 19.36 GFLOPS | Progress: (8/10) | 7.47 s
[Task 20/25] Current/Best: 8.93/ 19.36 GFLOPS | Progress: (10/10) | 8.38 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 3.28/ 14.68 GFLOPS | Progress: (4/10) | 6.66 s
[Task 1/25] Current/Best: 8.72/ 14.68 GFLOPS | Progress: (8/10) | 10.73 s
[Task 1/25] Current/Best: 13.92/ 16.88 GFLOPS | Progress: (10/10) | 11.74 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 10.15/ 16.52 GFLOPS | Progress: (4/10) | 2.15 s
[Task 2/25] Current/Best: 12.32/ 16.52 GFLOPS | Progress: (8/10) | 4.11 s
[Task 2/25] Current/Best: 11.26/ 16.52 GFLOPS | Progress: (10/10) | 4.80 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 13.26/ 13.26 GFLOPS | Progress: (4/10) | 4.88 s
[Task 3/25] Current/Best: 7.25/ 17.89 GFLOPS | Progress: (8/10) | 7.45 s
[Task 3/25] Current/Best: 17.52/ 20.39 GFLOPS | Progress: (10/10) | 8.30 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 10.97/ 17.60 GFLOPS | Progress: (4/10) | 9.18 s
[Task 4/25] Current/Best: 15.10/ 17.60 GFLOPS | Progress: (8/10) | 13.24 s
[Task 4/25] Current/Best: 13.77/ 17.60 GFLOPS | Progress: (10/10) | 14.75 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 20.76/ 20.76 GFLOPS | Progress: (4/10) | 2.92 s
[Task 5/25] Current/Best: 5.81/ 20.76 GFLOPS | Progress: (8/10) | 4.94 s
[Task 5/25] Current/Best: 4.17/ 20.76 GFLOPS | Progress: (10/10) | 6.28 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 13.50/ 19.06 GFLOPS | Progress: (4/10) | 3.47 s
[Task 6/25] Current/Best: 13.53/ 20.44 GFLOPS | Progress: (8/10) | 5.17 s
[Task 6/25] Current/Best: 14.25/ 20.44 GFLOPS | Progress: (10/10) | 6.55 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 23.25/ 23.26 GFLOPS | Progress: (4/10) | 3.26 s
[Task 7/25] Current/Best: 17.09/ 23.26 GFLOPS | Progress: (8/10) | 6.06 s
[Task 7/25] Current/Best: 16.00/ 23.26 GFLOPS | Progress: (10/10) | 7.01 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 10.83/ 10.83 GFLOPS | Progress: (4/10) | 4.29 s
[Task 8/25] Current/Best: 13.19/ 13.19 GFLOPS | Progress: (8/10) | 26.17 s
[Task 8/25] Current/Best: 11.15/ 13.19 GFLOPS | Progress: (10/10) | 28.21 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 15.30/ 15.78 GFLOPS | Progress: (4/10) | 4.48 s
[Task 9/25] Current/Best: 22.23/ 22.23 GFLOPS | Progress: (8/10) | 9.13 s
[Task 9/25] Current/Best: 3.53/ 22.23 GFLOPS | Progress: (10/10) | 14.42 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 16.32/ 20.37 GFLOPS | Progress: (4/10) | 2.28 s
[Task 10/25] Current/Best: 14.14/ 20.37 GFLOPS | Progress: (8/10) | 3.89 s
[Task 10/25] Current/Best: 8.75/ 20.37 GFLOPS | Progress: (10/10) | 4.67 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (4/10) | 3.19 s
[Task 11/25] Current/Best: 12.71/ 24.09 GFLOPS | Progress: (8/10) | 5.37 s
[Task 11/25] Current/Best: 12.90/ 24.09 GFLOPS | Progress: (10/10) | 6.21 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 16.55/ 17.92 GFLOPS | Progress: (4/10) | 3.06 s
[Task 12/25] Current/Best: 19.06/ 19.06 GFLOPS | Progress: (8/10) | 5.96 s
[Task 12/25] Current/Best: 10.07/ 19.06 GFLOPS | Progress: (10/10) | 7.36 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 6.32/ 20.45 GFLOPS | Progress: (4/10) | 3.13 s
[Task 13/25] Current/Best: 22.25/ 22.25 GFLOPS | Progress: (8/10) | 5.15 s
[Task 13/25] Current/Best: 1.56/ 22.25 GFLOPS | Progress: (10/10) | 7.86 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 19.79/ 19.79 GFLOPS | Progress: (4/10) | 4.77 s
[Task 14/25] Current/Best: 10.15/ 19.79 GFLOPS | Progress: (8/10) | 7.62 s
[Task 14/25] Current/Best: 6.64/ 19.79 GFLOPS | Progress: (10/10) | 8.56 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (4/10) | 3.31 s
[Task 21/25] Current/Best: 7.14/ 18.05 GFLOPS | Progress: (8/10) | 5.42 s
[Task 21/25] Current/Best: 13.11/ 18.05 GFLOPS | Progress: (10/10) | 6.62 s Done.
-
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (4/10) | 2.75 s
[Task 22/25] Current/Best: 5.29/ 19.72 GFLOPS | Progress: (8/10) | 5.95 s
[Task 22/25] Current/Best: 9.93/ 19.72 GFLOPS | Progress: (10/10) | 8.20 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 16.71/ 20.96 GFLOPS | Progress: (4/10) | 2.71 s
[Task 23/25] Current/Best: 14.12/ 20.96 GFLOPS | Progress: (8/10) | 4.88 s
[Task 23/25] Current/Best: 13.48/ 20.96 GFLOPS | Progress: (10/10) | 6.36 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 5.46/ 5.87 GFLOPS | Progress: (4/10) | 13.28 s
[Task 24/25] Current/Best: 2.48/ 10.38 GFLOPS | Progress: (8/10) | 21.36 s
[Task 24/25] Current/Best: 3.79/ 10.38 GFLOPS | Progress: (10/10) | 22.71 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
-
[Task 25/25] Current/Best: 5.63/ 5.63 GFLOPS | Progress: (4/10) | 2.09 s
[Task 25/25] Current/Best: 1.55/ 5.63 GFLOPS | Progress: (8/10) | 33.36 s
[Task 25/25] Current/Best: 8.97/ 8.97 GFLOPS | Progress: (10/10) | 34.21 s
+
[Task 15/25] Current/Best: 14.37/ 23.79 GFLOPS | Progress: (4/10) | 2.13 s
[Task 15/25] Current/Best: 6.71/ 23.79 GFLOPS | Progress: (8/10) | 4.35 s
[Task 15/25] Current/Best: 9.23/ 23.79 GFLOPS | Progress: (10/10) | 9.06 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 3.00/ 19.25 GFLOPS | Progress: (4/10) | 3.21 s
[Task 16/25] Current/Best: 17.82/ 21.96 GFLOPS | Progress: (8/10) | 4.31 s
[Task 16/25] Current/Best: 17.75/ 21.96 GFLOPS | Progress: (10/10) | 4.92 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 12.31/ 23.47 GFLOPS | Progress: (4/10) | 2.78 s
[Task 17/25] Current/Best: 17.16/ 23.47 GFLOPS | Progress: (8/10) | 4.84 s
[Task 17/25] Current/Best: 13.47/ 23.47 GFLOPS | Progress: (10/10) | 5.99 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/10) | 4.12 s
[Task 18/25] Current/Best: 8.05/ 18.14 GFLOPS | Progress: (8/10) | 9.30 s
[Task 18/25] Current/Best: 10.33/ 18.14 GFLOPS | Progress: (10/10) | 11.24 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 18.26/ 21.92 GFLOPS | Progress: (4/10) | 3.92 s
[Task 19/25] Current/Best: 18.20/ 21.92 GFLOPS | Progress: (8/10) | 8.41 s
[Task 19/25] Current/Best: 12.77/ 21.92 GFLOPS | Progress: (10/10) | 10.57 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 8.45/ 17.90 GFLOPS | Progress: (4/10) | 3.27 s
[Task 20/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (8/10) | 5.34 s
[Task 20/25] Current/Best: 14.25/ 19.01 GFLOPS | Progress: (10/10) | 5.96 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 5.12/ 17.70 GFLOPS | Progress: (4/10) | 2.87 s
[Task 21/25] Current/Best: 10.30/ 17.70 GFLOPS | Progress: (8/10) | 4.69 s
[Task 21/25] Current/Best: 6.99/ 17.70 GFLOPS | Progress: (10/10) | 5.80 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 12.97/ 15.39 GFLOPS | Progress: (4/10) | 3.45 s
[Task 22/25] Current/Best: 9.93/ 22.09 GFLOPS | Progress: (8/10) | 5.50 s
[Task 22/25] Current/Best: 5.34/ 22.09 GFLOPS | Progress: (10/10) | 6.39
s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 14.43/ 17.53 GFLOPS | Progress: (4/10) | 4.35 s
[Task 23/25] Current/Best: 12.97/ 19.37 GFLOPS | Progress: (8/10) | 6.99 s
[Task 23/25] Current/Best: 8.89/ 23.59 GFLOPS | Progress: (10/10) | 7.96 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 4.30/ 4.30 GFLOPS | Progress: (4/10) | 34.63 s Done.
+ Done.
+ Done.
+
[Task 24/25] Current/Best: 3.60/ 8.70 GFLOPS | Progress: (8/10) | 56.50 s
[Task 24/25] Current/Best: 5.20/ 8.70 GFLOPS | Progress: (10/10) | 66.90 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 25/25] Current/Best: 5.68/ 9.05 GFLOPS | Progress: (4/10) | 3.54 s
[Task 25/25] Current/Best: 5.81/ 9.05 GFLOPS | Progress: (8/10) | 6.19 s
[Task 25/25] Current/Best: 7.64/ 9.05 GFLOPS | Progress: (10/10) | 6.96 s Done.
+
The output from this tuning process will look something like this:
@@ -594,8 +595,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621102
- class='n02123159 tiger cat' with probability=0.356379
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -648,8 +649,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.7892823800016, 'median': 417.7939836500059, 'std': 0.5207584102190087}
- unoptimized: {'mean': 494.3400694800004, 'median': 493.9094355999998, 'std': 1.1932189175639154}
+ optimized: {'mean': 428.3857485400017, 'median': 428.4126755999978, 'std': 0.6424460229291523}
+ unoptimized: {'mean': 491.7812707299992, 'median': 491.7406261499991, 'std': 0.606950351019823}
@@ -669,7 +670,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 59.729 seconds)
+ **Total running time of the script:** ( 7 minutes 49.457 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 627766b2c..4cd3194d8 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.257e-07 secs/op
+ 1.276e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index b46416b0a..49150f98f 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -233,7 +233,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x2322a160)), stage(b, placeholder(b, 0x232ebc80)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0xe7ae3a0)), stage(b, placeholder(b, 0xe0554d0)), 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 68ddb940b..271a9bdd0 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**09:42.321** total execution time for **tutorial** files:
+**10:41.220** total execution time for **tutorial** files:
-- **06:59.729**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:00.942**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:53.033**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:25.745**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:20.643**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.153**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.703**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.194**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.055**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.042**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.042**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.040**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **07:49.457**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **00:58.813**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:58.451**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:26.207**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:26.040**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:01.211**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.713**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.199**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.037**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.031**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.030**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.030**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 1e0ec8830..7491581c8 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -243,7 +243,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000006
@@ -388,7 +388,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000024
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -438,10 +438,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.137820000229112e-06 1.0
- naive 5.8405e-06 0.7176983516267952
- parallel 6.0809e-06 0.7472394326525774
- vector 2.4667e-05 3.031155763989069
+ numpy 7.180989998687437e-06 1.0
+ naive 6.1019e-06 0.8497296335345577
+ parallel 6.112399999999999e-06 0.8511918274663023
+ vector 2.4469599999999997e-05 3.4075524411637703
@@ -830,7 +830,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017685
+ Numpy running time: 0.018402
@@ -886,7 +886,7 @@ optimizations.
.. code-block:: none
- none: 3.425653
+ none: 3.253881
@@ -985,7 +985,7 @@ schedule.
.. code-block:: none
- blocking: 0.299216
+ blocking: 0.301795
@@ -1077,7 +1077,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.334286
+ vectorization: 0.336453
@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], []),
@@ -1149,7 +1149,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118259
+ loop permutation: 0.114948
@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], []),
@@ -1246,7 +1246,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109103
+ array packing: 0.107904
@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], []),
@@ -1337,7 +1337,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110817
+ block caching: 0.110984
@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], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.143928
+ parallelization: 0.144506
@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], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4256529191 1.0
- blocking 0.2992160025 0.08734568549887159
- vectorization 0.33428597829999995 0.09758314289114403
- loop permutation 0.1182592719 0.034521673588306635
- array packing 0.10910253610000001 0.03184868364558772
- block caching 0.11081700940000001 0.032349164383271574
- parallelization 0.1439280894 0.04201479040609091
+ none 3.2538812269 1.0
+ blocking 0.30179535830000004 0.09274934678163499
+ vectorization 0.3364530468 0.10340053103921733
+ loop permutation 0.11494751169999999 0.03532627766180373
+ array packing 0.1079040546 0.03316164514793955
+ block caching 0.11098448289999999 0.03410833867643529
+ parallelization 0.1445058061 0.044410289135744484
@@ -1541,11 +1541,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.942 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 12bbc94e2..3ddb7233f 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-b772d272735df025cf1ca0959a678f543c94ece5
+552f06ed450d59816eb3a85f7e810d9726dcce26
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 99094d633..2bd696a21 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb40a7ce6-98d9-4390-bb65-14c407749571 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipeccbf69f-00ae-4432-87a2-b99dccae5fad 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 e82179b0d..716fac026 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,45 +406,48 @@ 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]
- 0%| | 16.0k/41.5M [00:00<08:09, 88.9kB/s]
- 0%| | 48.0k/41.5M [00:00<05:09, 141kB/s]
- 0%| | 96.0k/41.5M [00:00<03:39, 198kB/s]
- 0%| | 208k/41.5M [00:00<01:58, 364kB/s]
- 1%| | 304k/41.5M [00:00<01:41, 424kB/s]
- 1%|1 | 600k/41.5M [00:01<00:51, 836kB/s]
- 3%|2 | 1.16M/41.5M [00:01<00:26, 1.62MB/s]
- 6%|5 | 2.29M/41.5M [00:01<00:13, 3.14MB/s]
- 9%|9 | 3.77M/41.5M [00:01<00:08, 4.77MB/s]
- 13%|#2 | 5.24M/41.5M [00:01<00:06, 5.88MB/s]
- 16%|#6 | 6.71M/41.5M [00:02<00:05, 6.63MB/s]
- 20%|#9 | 8.19M/41.5M [00:02<00:04, 7.15MB/s]
- 23%|##3 | 9.66M/41.5M [00:02<00:04, 7.50MB/s]
- 27%|##6 | 11.1M/41.5M [00:02<00:04, 7.75MB/s]
- 30%|### | 12.6M/41.5M [00:02<00:03, 8.86MB/s]
- 34%|###3 | 14.0M/41.5M [00:02<00:02, 10.1MB/s]
- 36%|###6 | 15.1M/41.5M [00:02<00:03, 9.11MB/s]
- 39%|###8 | 16.0M/41.5M [00:03<00:03, 7.81MB/s]
- 41%|#### | 17.0M/41.5M [00:03<00:03, 7.50MB/s]
- 45%|####4 | 18.5M/41.5M [00:03<00:03, 7.75MB/s]
- 48%|####8 | 19.9M/41.5M [00:03<00:02, 9.22MB/s]
- 50%|##### | 20.9M/41.5M [00:03<00:02, 9.15MB/s]
- 53%|#####2 | 21.8M/41.5M [00:03<00:02, 7.79MB/s]
- 55%|#####5 | 22.9M/41.5M [00:04<00:02, 7.23MB/s]
- 59%|#####8 | 24.3M/41.5M [00:04<00:02, 8.90MB/s]
- 62%|######2 | 25.7M/41.5M [00:04<00:01, 10.1MB/s]
- 65%|######4 | 26.8M/41.5M [00:04<00:01, 8.78MB/s]
- 67%|######6 | 27.7M/41.5M [00:04<00:01, 7.58MB/s]
- 69%|######9 | 28.8M/41.5M [00:04<00:01, 7.06MB/s]
- 73%|#######2 | 30.2M/41.5M [00:04<00:01, 8.04MB/s]
- 76%|#######6 | 31.7M/41.5M [00:05<00:01, 8.21MB/s]
- 80%|#######9 | 33.1M/41.5M [00:05<00:00, 9.51MB/s]
- 82%|########2 | 34.1M/41.5M [00:05<00:00, 8.99MB/s]
- 84%|########4 | 35.0M/41.5M [00:05<00:00, 7.68MB/s]
- 87%|########6 | 36.1M/41.5M [00:05<00:00, 7.83MB/s]
- 90%|######### | 37.5M/41.5M [00:05<00:00, 7.36MB/s]
- 94%|#########3| 39.0M/41.5M [00:06<00:00, 7.64MB/s]
- 98%|#########7| 40.5M/41.5M [00:06<00:00, 7.84MB/s]
-100%|##########| 41.5M/41.5M [00:06<00:00, 6.90MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:33, 84.6kB/s]
+ 0%| | 48.0k/41.5M [00:00<05:34, 130kB/s]
+ 0%| | 96.0k/41.5M [00:00<04:10, 174kB/s]
+ 0%| | 160k/41.5M [00:00<03:09, 229kB/s]
+ 1%| | 328k/41.5M [00:01<01:36, 447kB/s]
+ 1%|1 | 544k/41.5M [00:01<01:04, 666kB/s]
+ 3%|2 | 1.06M/41.5M [00:01<00:31, 1.33MB/s]
+ 5%|4 | 1.99M/41.5M [00:01<00:16, 2.45MB/s]
+ 8%|8 | 3.46M/41.5M [00:01<00:09, 4.11MB/s]
+ 12%|#1 | 4.93M/41.5M [00:02<00:07, 5.14MB/s]
+ 15%|#5 | 6.41M/41.5M [00:02<00:06, 5.87MB/s]
+ 19%|#8 | 7.88M/41.5M [00:02<00:05, 6.31MB/s]
+ 23%|##2 | 9.34M/41.5M [00:02<00:05, 6.54MB/s]
+ 26%|##6 | 10.8M/41.5M [00:02<00:04, 6.78MB/s]
+ 30%|##9 | 12.3M/41.5M [00:03<00:04, 6.93MB/s]
+ 33%|###3 | 13.8M/41.5M [00:03<00:04, 7.10MB/s]
+ 37%|###6 | 15.2M/41.5M [00:03<00:03, 8.35MB/s]
+ 39%|###8 | 16.1M/41.5M [00:03<00:03, 8.38MB/s]
+ 41%|#### | 17.0M/41.5M [00:03<00:03, 7.00MB/s]
+ 44%|####3 | 18.1M/41.5M [00:03<00:03, 7.99MB/s]
+ 46%|####5 | 19.0M/41.5M [00:03<00:02, 8.13MB/s]
+ 48%|####7 | 19.8M/41.5M [00:04<00:03, 6.49MB/s]
+ 51%|##### | 21.1M/41.5M [00:04<00:03, 6.29MB/s]
+ 54%|#####4 | 22.6M/41.5M [00:04<00:03, 6.52MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:04<00:02, 6.63MB/s]
+ 61%|######1 | 25.5M/41.5M [00:05<00:02, 6.67MB/s]
+ 65%|######4 | 26.9M/41.5M [00:05<00:01, 8.04MB/s]
+ 67%|######7 | 27.8M/41.5M [00:05<00:01, 8.03MB/s]
+ 69%|######9 | 28.6M/41.5M [00:05<00:01, 6.78MB/s]
+ 72%|#######1 | 29.9M/41.5M [00:05<00:01, 7.96MB/s]
+ 74%|#######4 | 30.7M/41.5M [00:05<00:01, 8.08MB/s]
+ 76%|#######6 | 31.6M/41.5M [00:05<00:01, 6.58MB/s]
+ 79%|#######9 | 32.8M/41.5M [00:05<00:01, 7.81MB/s]
+ 81%|########1 | 33.6M/41.5M [00:06<00:01, 7.76MB/s]
+ 83%|########3 | 34.5M/41.5M [00:06<00:01, 6.42MB/s]
+ 86%|########6 | 35.8M/41.5M [00:06<00:00, 7.64MB/s]
+ 89%|########9 | 36.9M/41.5M [00:06<00:00, 8.74MB/s]
+ 91%|#########1| 37.9M/41.5M [00:06<00:00, 7.65MB/s]
+ 93%|#########3| 38.7M/41.5M [00:06<00:00, 7.37MB/s]
+ 96%|#########6| 39.9M/41.5M [00:06<00:00, 8.41MB/s]
+ 98%|#########8| 40.7M/41.5M [00:07<00:00, 7.30MB/s]
+100%|##########| 41.5M/41.5M [00:07<00:00, 6.10MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 7d8d5dff7..9052807bf 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -464,7 +464,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.658 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.918 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.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_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index e5e385e02..6be070511 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,10 +387,9 @@ 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]
- 9%|9 | 4.17M/44.7M [00:00<00:00, 43.7MB/s]
- 19%|#8 | 8.34M/44.7M [00:00<00:00, 41.0MB/s]
- 67%|######6 | 29.8M/44.7M [00:00<00:00, 122MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 124MB/s]
+ 37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
+ 83%|########3 | 37.2M/44.7M [00:00<00:00, 198MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 186MB/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 ac9a132cc..5dd595095 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -607,7 +607,6 @@ 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 2.941 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download 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 14b280480..d32e74444 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<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>05:17.383</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:15.477</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:05.658</strong>: <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></li>
-<li><p><strong>01:02.941</strong>: <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></li>
-<li><p><strong>00:55.811</strong>: <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></li>
-<li><p><strong>00:30.013</strong>: <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></li>
-<li><p><strong>00:25.255</strong>: <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></li>
-<li><p><strong>00:21.744</strong>: <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></li>
-<li><p><strong>00:20.696</strong>: <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></li>
-<li><p><strong>00:19.257</strong>: <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></li>
-<li><p><strong>00:13.417</strong>: <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></li>
-<li><p><strong>00:02.593</strong>: <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></li>
+<li><p><strong>01:06.918</strong>: <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></li>
+<li><p><strong>00:59.815</strong>: <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></li>
+<li><p><strong>00:55.491</strong>: <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></li>
+<li><p><strong>00:31.087</strong>: <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></li>
+<li><p><strong>00:25.177</strong>: <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></li>
+<li><p><strong>00:21.531</strong>: <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></li>
+<li><p><strong>00:20.848</strong>: <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></li>
+<li><p><strong>00:18.629</strong>: <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></li>
+<li><p><strong>00:13.297</strong>: <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></li>
+<li><p><strong>00:02.684</strong>: <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></li>
</ul>
</div>
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 720a25bcb..b3df563e1 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6744 15.6781 15.7798 15.5871 0.0616
+ 15.9735 15.9725 16.1387 15.8400 0.0920
</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 441242eb7..0d30c82e2 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,44 +409,24 @@ 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 | 4.06M/170M [00:00<00:04, 42.3MB/s]
- 6%|5 | 9.72M/170M [00:00<00:03, 52.3MB/s]
- 9%|8 | 14.7M/170M [00:00<00:03, 49.2MB/s]
- 12%|#1 | 19.6M/170M [00:00<00:03, 49.5MB/s]
- 15%|#4 | 25.1M/170M [00:00<00:02, 52.3MB/s]
- 18%|#7 | 30.2M/170M [00:00<00:02, 52.9MB/s]
- 21%|## | 35.3M/170M [00:00<00:02, 49.6MB/s]
- 24%|##4 | 41.1M/170M [00:00<00:02, 52.3MB/s]
- 27%|##7 | 46.1M/170M [00:00<00:02, 45.5MB/s]
- 30%|##9 | 50.6M/170M [00:01<00:03, 38.2MB/s]
- 33%|###2 | 55.7M/170M [00:01<00:02, 41.8MB/s]
- 35%|###5 | 59.9M/170M [00:01<00:02, 41.9MB/s]
- 38%|###7 | 64.1M/170M [00:01<00:02, 40.2MB/s]
- 40%|#### | 68.1M/170M [00:01<00:03, 34.5MB/s]
- 42%|####2 | 71.6M/170M [00:02<00:05, 20.4MB/s]
- 44%|####3 | 74.3M/170M [00:02<00:04, 21.2MB/s]
- 47%|####6 | 79.7M/170M [00:02<00:03, 27.9MB/s]
- 49%|####8 | 83.2M/170M [00:02<00:03, 29.7MB/s]
- 51%|#####1 | 86.8M/170M [00:02<00:02, 31.2MB/s]
- 53%|#####3 | 90.7M/170M [00:02<00:02, 33.6MB/s]
- 56%|#####5 | 95.0M/170M [00:02<00:02, 36.5MB/s]
- 58%|#####8 | 99.3M/170M [00:02<00:01, 38.8MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 41.9MB/s]
- 64%|######3 | 108M/170M [00:02<00:01, 42.8MB/s]
- 66%|######6 | 113M/170M [00:03<00:01, 35.7MB/s]
- 69%|######8 | 117M/170M [00:03<00:01, 37.0MB/s]
- 71%|#######1 | 121M/170M [00:03<00:01, 38.9MB/s]
- 74%|#######3 | 125M/170M [00:03<00:01, 40.2MB/s]
- 77%|#######6 | 130M/170M [00:03<00:00, 44.3MB/s]
- 80%|#######9 | 135M/170M [00:03<00:00, 46.4MB/s]
- 83%|########2 | 141M/170M [00:03<00:00, 49.2MB/s]
- 86%|########5 | 146M/170M [00:03<00:00, 50.3MB/s]
- 89%|########8 | 151M/170M [00:04<00:00, 44.8MB/s]
- 92%|#########1| 156M/170M [00:04<00:00, 46.2MB/s]
- 94%|#########4| 160M/170M [00:04<00:00, 41.9MB/s]
- 97%|#########6| 164M/170M [00:04<00:00, 42.6MB/s]
- 99%|#########9| 169M/170M [00:04<00:00, 40.8MB/s]
-100%|##########| 170M/170M [00:04<00:00, 39.7MB/s]
+ 6%|5 | 9.83M/170M [00:00<00:01, 103MB/s]
+ 12%|#1 | 19.7M/170M [00:00<00:01, 92.6MB/s]
+ 17%|#7 | 28.9M/170M [00:00<00:01, 94.6MB/s]
+ 23%|##2 | 38.8M/170M [00:00<00:01, 97.8MB/s]
+ 28%|##8 | 48.1M/170M [00:00<00:01, 86.4MB/s]
+ 33%|###3 | 56.6M/170M [00:00<00:01, 84.6MB/s]
+ 39%|###8 | 65.8M/170M [00:00<00:01, 88.1MB/s]
+ 44%|####4 | 74.8M/170M [00:00<00:01, 90.0MB/s]
+ 49%|####9 | 83.5M/170M [00:00<00:01, 83.4MB/s]
+ 55%|#####5 | 93.8M/170M [00:01<00:00, 89.8MB/s]
+ 60%|###### | 103M/170M [00:01<00:00, 90.1MB/s]
+ 65%|######5 | 111M/170M [00:01<00:00, 84.9MB/s]
+ 71%|#######1 | 121M/170M [00:01<00:00, 90.6MB/s]
+ 77%|#######6 | 131M/170M [00:01<00:00, 93.1MB/s]
+ 83%|########3 | 142M/170M [00:01<00:00, 99.3MB/s]
+ 89%|########9 | 152M/170M [00:01<00:00, 101MB/s]
+ 95%|#########5| 162M/170M [00:01<00:00, 90.9MB/s]
+100%|##########| 170M/170M [00:01<00:00, 89.6MB/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').
@@ -539,7 +519,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 6.931 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 4.101 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download 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 eadeb9b62..3405f2e93 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,7 @@ 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]
-100%|##########| 13.6M/13.6M [00:00<00:00, 178MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 180MB/s]
</pre></div>
</div>
</div>
@@ -539,7 +539,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<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)
- 90.2875 90.1954 91.3833 90.0761 0.2433
+ 90.3897 90.2330 92.7423 89.9795 0.3807
</pre></div>
</div>
<div class="admonition note">
@@ -578,7 +578,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.243 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.622 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download 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 753f5efe9..1a55a4527 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.4826 120.3870 125.9365 119.0509 0.8410
+ 119.5120 119.4274 121.5809 118.4995 0.4991
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 6.508 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 56.016 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download 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 fd1072c97..a9d60cea9 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ 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 25.587 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.968 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download 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 bc5b9a7a6..3ab8f53c4 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,24 +415,24 @@ 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]
- 0%| | 123/132723 [00:00<01:52, 1174.93KB/s]
- 5%|4 | 6216/132723 [00:00<00:03, 35658.17KB/s]
- 11%|# | 14185/132723 [00:00<00:02, 55550.64KB/s]
- 17%|#6 | 22359/132723 [00:00<00:01, 65821.34KB/s]
- 23%|##3 | 30632/132723 [00:00<00:01, 71890.82KB/s]
- 29%|##9 | 38918/132723 [00:00<00:01, 75606.55KB/s]
- 35%|###5 | 47046/132723 [00:00<00:01, 77452.15KB/s]
- 42%|####1 | 55277/132723 [00:00<00:00, 78986.27KB/s]
- 48%|####7 | 63446/132723 [00:00<00:00, 79829.24KB/s]
- 54%|#####3 | 71669/132723 [00:01<00:00, 80565.82KB/s]
- 60%|###### | 79920/132723 [00:01<00:00, 81156.58KB/s]
- 66%|######6 | 88131/132723 [00:01<00:00, 81443.10KB/s]
- 73%|#######2 | 96329/132723 [00:01<00:00, 81604.37KB/s]
- 79%|#######8 | 104550/132723 [00:01<00:00, 81785.63KB/s]
- 85%|########4 | 112730/132723 [00:01<00:00, 81765.43KB/s]
- 91%|#########1| 121031/132723 [00:01<00:00, 82136.82KB/s]
- 97%|#########7| 129290/132723 [00:01<00:00, 82271.61KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75977.13KB/s]
+ 3%|2 | 3469/132723 [00:00<00:03, 34420.94KB/s]
+ 7%|6 | 8811/132723 [00:00<00:02, 45556.38KB/s]
+ 13%|#2 | 16679/132723 [00:00<00:01, 60652.65KB/s]
+ 19%|#8 | 24681/132723 [00:00<00:01, 68288.44KB/s]
+ 25%|##4 | 32729/132723 [00:00<00:01, 72675.72KB/s]
+ 31%|### | 40742/132723 [00:00<00:01, 75206.24KB/s]
+ 37%|###6 | 48808/132723 [00:00<00:01, 76987.35KB/s]
+ 43%|####2 | 56841/132723 [00:00<00:00, 78048.74KB/s]
+ 49%|####8 | 64647/132723 [00:00<00:00, 77763.41KB/s]
+ 55%|#####4 | 72448/132723 [00:01<00:00, 77835.59KB/s]
+ 60%|###### | 80248/132723 [00:01<00:00, 77876.25KB/s]
+ 66%|######6 | 88037/132723 [00:01<00:00, 77740.81KB/s]
+ 72%|#######2 | 95812/132723 [00:01<00:00, 77595.04KB/s]
+ 78%|#######8 | 103608/132723 [00:01<00:00, 77701.18KB/s]
+ 84%|########3 | 111379/132723 [00:01<00:00, 77457.54KB/s]
+ 90%|########9 | 119126/132723 [00:01<00:00, 77329.54KB/s]
+ 96%|#########5| 126864/132723 [00:01<00:00, 77340.81KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 74499.40KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -472,7 +472,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.499 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.450 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download 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 89c37c093..18b20ebaa 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>10:55.932</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:27.704</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:06.931</strong>: <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></li>
-<li><p><strong>02:22.499</strong>: <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></li>
-<li><p><strong>02:06.508</strong>: <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></li>
-<li><p><strong>01:25.587</strong>: <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></li>
-<li><p><strong>01:04.243</strong>: <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></li>
-<li><p><strong>00:27.947</strong>: <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></li>
-<li><p><strong>00:22.029</strong>: <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></li>
-<li><p><strong>00:00.188</strong>: <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></li>
+<li><p><strong>03:04.101</strong>: <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></li>
+<li><p><strong>02:22.450</strong>: <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></li>
+<li><p><strong>01:56.016</strong>: <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></li>
+<li><p><strong>01:10.968</strong>: <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></li>
+<li><p><strong>01:04.622</strong>: <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></li>
+<li><p><strong>00:27.896</strong>: <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></li>
+<li><p><strong>00:21.451</strong>: <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></li>
+<li><p><strong>00:00.202</strong>: <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></li>
</ul>
</div>
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 2632df37e..de9aff35a 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip9a4dd0be-f3aa-40f1-bbd1-ffd3329b9539 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.zipb1c37f6d-754c-4b34-aca9-d8ed44396371 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 8e75db064..54e462b90 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<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>00:38.152</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.957</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.636</strong>: <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></li>
-<li><p><strong>00:02.258</strong>: <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></li>
-<li><p><strong>00:01.061</strong>: <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></li>
-<li><p><strong>00:00.198</strong>: <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></li>
+<li><p><strong>00:34.493</strong>: <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></li>
+<li><p><strong>00:02.229</strong>: <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></li>
+<li><p><strong>00:01.040</strong>: <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></li>
+<li><p><strong>00:00.194</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 2fa6d90f0..86e012a8c 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6019us [6019us] (45.46%; 45.46%)
-FoldScaleAxis: 7221us [2us] (54.54%; 54.54%)
- FoldConstant: 7219us [1511us] (54.52%; 99.97%)
- InferType: 5708us [5708us] (43.11%; 79.07%)
+InferType: 5847us [5847us] (44.94%; 44.94%)
+FoldScaleAxis: 7163us [2us] (55.06%; 55.06%)
+ FoldConstant: 7161us [1488us] (55.04%; 99.97%)
+ InferType: 5673us [5673us] (43.61%; 79.22%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5774us [5774us] (44.49%; 44.49%)
-FoldScaleAxis: 7205us [2us] (55.51%; 55.51%)
- FoldConstant: 7203us [1479us] (55.50%; 99.98%)
- InferType: 5724us [5724us] (44.10%; 79.46%)
+InferType: 5683us [5683us] (44.20%; 44.20%)
+FoldScaleAxis: 7173us [2us] (55.80%; 55.80%)
+ FoldConstant: 7171us [1510us] (55.78%; 99.98%)
+ InferType: 5661us [5661us] (44.04%; 78.94%)
</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 98cc6e2e1..ddf254870 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 44.075864 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.134968 ms
</pre></div>
</div>
<div class="sphx-glr-footer class 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 20eb238bc..cce10f835 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.736506 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.091136 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 3183932c1..f6e7fb3b7 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018356
-Baseline: 3.414940
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018117
+Baseline: 3.197863
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -494,7 +494,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301714
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.302272
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -563,7 +563,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336810
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.341488
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -626,7 +626,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116738
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120279
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -711,7 +711,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110333
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111055
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111412
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111010
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -891,7 +891,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145097
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144610
</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 2ef20695a..dcbf77a03 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:35.069</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.438</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.405</strong>: <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></li>
-<li><p><strong>00:01.447</strong>: <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></li>
-<li><p><strong>00:01.216</strong>: <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></li>
+<li><p><strong>00:31.826</strong>: <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></li>
+<li><p><strong>00:01.414</strong>: <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></li>
+<li><p><strong>00:01.197</strong>: <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></li>
</ul>
</div>
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 45004f4ec..330b8364f 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<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>04:51.474</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>04:55.482</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:16.560</strong>: <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></li>
-<li><p><strong>01:20.012</strong>: <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></li>
-<li><p><strong>00:40.421</strong>: <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></li>
-<li><p><strong>00:17.102</strong>: <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></li>
-<li><p><strong>00:08.869</strong>: <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></li>
-<li><p><strong>00:08.510</strong>: <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></li>
+<li><p><strong>02:20.906</strong>: <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></li>
+<li><p><strong>01:19.998</strong>: <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></li>
+<li><p><strong>00:40.306</strong>: <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></li>
+<li><p><strong>00:17.326</strong>: <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></li>
+<li><p><strong>00:08.590</strong>: <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></li>
+<li><p><strong>00:08.355</strong>: <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></li>
</ul>
</div>
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 76eb3e688..99079d1e9 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
@@ -470,240 +470,689 @@ 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, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*3136)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*576)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 112), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 112), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 224), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 224), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 336), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 336), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 448), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 448), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 560), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 560), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 672), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 672), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 896), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 896), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1120), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1120), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1232), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1232), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1344), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1344), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1456), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1456), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1680), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1680), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1792), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1792), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1904), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1904), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1560)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2128), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2128), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2128), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2240), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2240), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2240), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2352), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2464), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2464), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2464), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2576), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2576), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2576), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2688)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2688), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2688), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2688), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2800)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2800), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2800), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2800), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 2912)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2912), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2912), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2912), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3024)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2344)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3136), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3248)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3248), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3248), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3248), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3360)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3360), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3360), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3360), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3472)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3472), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3472), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3472), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3584)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3584), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3584), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3584), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3696)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3696), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3696), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3696), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3808)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3808), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3808), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3808), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3920), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3920), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3920), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[(threadIdx.x_2*4)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 448), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 449)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 449), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 450)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 451)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 448), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 896), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 897)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 898)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 898), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 899)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 896), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 1344)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 32256)]
- kernel.shared_1[((threadIdx.x_2*4) + 1345)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1345), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 32256)]
- kernel.shared_1[((threadIdx.x_2*4) + 1346)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1346), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 32256)]
- kernel.shared_1[((threadIdx.x_2*4) + 1347)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 32256)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 1792)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1792), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1793)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 1793), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1794)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 1795)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 1792), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2240), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2241)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2242)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2242), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 2243)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 2240), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 2688)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*4) + 2689)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2689), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*4) + 2690)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 2690), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*4) + 2691)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 64512)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3136), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3137)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3137), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3138)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3139)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 3136), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 3584)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3584), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3585)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3586)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 3586), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 3587)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 3584), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 4032)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 96768)]
- kernel.shared_1[((threadIdx.x_2*4) + 4033)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4033), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 96768)]
- kernel.shared_1[((threadIdx.x_2*4) + 4034)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4034), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 96768)]
- kernel.shared_1[((threadIdx.x_2*4) + 4035)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 96768)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 4480)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4480), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4481)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4481), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4482)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4483)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 4480), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 4928)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4928), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4929)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 43), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4930)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 4930), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- kernel.shared_1[((threadIdx.x_2*4) + 4931)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 4928), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*4) + 5376)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2*4), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*4) + 5377)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5377), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*4) + 5378)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5378), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*4) + 5379)] = kernel[(((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 16), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 1), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3)) + 129024)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5824)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5824), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5825)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floordiv(floormod(((threadIdx.x_2*4) + 5825), 192), 3)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 2), 3))]
- }
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5826)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floormod((floordiv((threadIdx.x_2*4), 3) + 22), 64)*9)) + cse_var_1) + floormod((threadIdx.x_2*4), 3))]
- }
- if @tir.likely((threadIdx.x_2 < 80), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*4) + 5827)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 3)*4608)) + cse_var_2) + (floormod((floordiv(((threadIdx.x_2*4) + 5824), 3) + 1), 64)*9)) + cse_var_1) + floormod(((threadIdx.x_2*4) + 1), 3))]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 32) {
- let cse_var_11: int32 = (ff.outer.inner*7)
- let cse_var_10: int32 = (cse_var_11 + 6)
- let cse_var_9: int32 = (cse_var_11 + 5)
- let cse_var_8: int32 = (cse_var_11 + 4)
- let cse_var_7: int32 = (cse_var_11 + 3)
- let cse_var_6: int32 = (cse_var_11 + 2)
- let cse_var_5: int32 = (cse_var_11 + 1)
- {
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[(((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3))]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 1)]))
- conv2d_nchw_1[cse_var_11] = (conv2d_nchw_1[cse_var_11] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.outer.inner*2016) + (rc.inner*63)) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*384) + (ff.outer.inner*192)) + (rc.outer.inner*96)) + (rc.inner*3)) + 2)]))
- }
- }
- }
- }
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 9)*7)) + (floormo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 9)*7)) + (fl [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 192), 27), 9)*7)) + ( [...]
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 312), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 408), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 424), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 440), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 456), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 472), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 488), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 520), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 536), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 552), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 568), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
- }
+ compute[(((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
}
}
</pre></div>
@@ -740,7 +1189,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.336 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.260 ms
</pre></div>
</div>
</div>
@@ -771,36 +1220,36 @@ 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=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=16)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=7)
+conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, 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=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_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=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=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=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
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])
@@ -817,16 +1266,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=4)
+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=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
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=112)
+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", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -844,10 +1293,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[6144];
+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[7];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -855,151 +1304,599 @@ extern "C" __global__ void __launch_bounds__(112) default_function_ker
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1560)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2128) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2240) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2464) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2576)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2576) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2688)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2688) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2800)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2800) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2912)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2912) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3024)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2344)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3248)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3248) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3360)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3360) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3472)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3472) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3584)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3584) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3696)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3696) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3808)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3808) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[(((int)threadIdx.x) * 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 1) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) % 48) * 4) + 2) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 449)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 450)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 451)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 448) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 897)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 898)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 899)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 896) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1344)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1345)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1346)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1347)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 4) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1793)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1794)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 1795)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 1792) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2241)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2242)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2243)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 2240) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 2688)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2689)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2690)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 2691)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 4) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3137)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3138)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3139)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 3136) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3584)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3585)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3586)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 3587)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 3584) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4032)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4033)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4034)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4035)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 96768)];
- kernel_shared[((((int)threadIdx.x) * 4) + 4480)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4481)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4482)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4483)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 4480) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4928)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4929)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 43) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4930)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 130) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 4931)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 4928) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- kernel_shared[((((int)threadIdx.x) * 4) + 5376)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) % 48) * 4) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 4) + 5377)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 1) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 4) + 5378)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 2) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 4) + 5379)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3)) + 129024)];
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5824)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 64) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- }
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5825)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) + 65) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 2) % 3))];
- }
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5826)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + (((((((int)threadIdx.x) * 4) / 3) + 22) & 63) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 4) % 3))];
- }
- if (((int)threadIdx.x) < 80) {
- kernel_shared[((((int)threadIdx.x) * 4) + 5827)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 48) * 4608)) + (rc_outer_outer * 576)) + ((((((((int)threadIdx.x) * 4) + 5824) / 3) + 1) & 63) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 4) + 1) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 32; ++rc_inner) {
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[(((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3))]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 1)]));
- conv2d_nchw[(ff_outer_inner * 7)] = (conv2d_nchw[(ff_outer_inner * 7)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 1)] = (conv2d_nchw[((ff_outer_inner * 7) + 1)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 2)] = (conv2d_nchw[((ff_outer_inner * 7) + 2)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 3)] = (conv2d_nchw[((ff_outer_inner * 7) + 3)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 4)] = (conv2d_nchw[((ff_outer_inner * 7) + 4)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 5)] = (conv2d_nchw[((ff_outer_inner * 7) + 5)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 7) + 6)] = (conv2d_nchw[((ff_outer_inner * 7) + 6)] + (pad_temp_shared[((((rc_outer_inner * 2016) + (rc_inner * 63)) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 384) + (ff_outer_inner * 192)) + (rc_outer_inner * 96)) + (rc_inner * 3)) + 2)]));
- }
- }
- }
- }
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((in [...]
+ if (((int)threadIdx.x) < 24) {
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= ((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) + 3) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int [...]
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -1036,7 +1933,7 @@ 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> ( 2 minutes 16.560 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.906 seconds)</p>
<div class="sphx-glr-footer class 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 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 9936d38bd..04b137a53 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ 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)
- 10.0346 10.0229 10.0847 9.9962 0.0371
+ 9.7771 9.7825 9.8053 9.7436 0.0255
</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 11e507c21..5a7954e52 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ 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)
- 760.1481 761.7492 765.0381 753.6569 4.7823
+ 765.3085 765.3539 767.8644 762.7072 2.1057
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ 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 20.012 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.998 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download 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 9618b1e5f..ec2d2557e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,74 +600,407 @@ 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_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (i.inner.init*16)
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ let cse_var_2: int32 = (nb_j.inner*16)
+ let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
{
- compute_5: Buffer(compute_4, float32, [1024], [])[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
- }
- }
- 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, 64) {
- let cse_var_21: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_20: int32 = (i.inner*16)
- let cse_var_19: int32 = (elem_idx*16)
- let cse_var_18: int32 = (cse_var_20 + 10)
- let cse_var_17: int32 = (cse_var_20 + 11)
- let cse_var_16: int32 = (cse_var_20 + 12)
- let cse_var_15: int32 = (cse_var_20 + 13)
- let cse_var_14: int32 = (cse_var_20 + 14)
- let cse_var_13: int32 = (cse_var_20 + 15)
- let cse_var_12: int32 = (cse_var_20 + 2)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 4)
- let cse_var_9: int32 = (cse_var_20 + 5)
- let cse_var_8: int32 = (cse_var_20 + 6)
- let cse_var_7: int32 = (cse_var_20 + 7)
- let cse_var_6: int32 = (cse_var_20 + 8)
- let cse_var_5: int32 = (cse_var_20 + 9)
- let cse_var_4: int32 = (cse_var_20 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.inner*256))
- {
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_19)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_19) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5: Buffer(compute_4, float32, [256], [])[cse_var_2] = 0f32
+ compute_5[(cse_var_2 + 1)] = 0f32
+ compute_5[(cse_var_2 + 2)] = 0f32
+ compute_5[(cse_var_2 + 3)] = 0f32
+ compute_5[(cse_var_2 + 4)] = 0f32
+ compute_5[(cse_var_2 + 5)] = 0f32
+ compute_5[(cse_var_2 + 6)] = 0f32
+ compute_5[(cse_var_2 + 7)] = 0f32
+ compute_5[(cse_var_2 + 8)] = 0f32
+ compute_5[(cse_var_2 + 9)] = 0f32
+ compute_5[(cse_var_2 + 10)] = 0f32
+ compute_5[(cse_var_2 + 11)] = 0f32
+ compute_5[(cse_var_2 + 12)] = 0f32
+ compute_5[(cse_var_2 + 13)] = 0f32
+ compute_5[(cse_var_2 + 14)] = 0f32
+ compute_5[(cse_var_2 + 15)] = 0f32
+ compute_5[(cse_var_2 + 32)] = 0f32
+ compute_5[(cse_var_2 + 33)] = 0f32
+ compute_5[(cse_var_2 + 34)] = 0f32
+ compute_5[(cse_var_2 + 35)] = 0f32
+ compute_5[(cse_var_2 + 36)] = 0f32
+ compute_5[(cse_var_2 + 37)] = 0f32
+ compute_5[(cse_var_2 + 38)] = 0f32
+ compute_5[(cse_var_2 + 39)] = 0f32
+ compute_5[(cse_var_2 + 40)] = 0f32
+ compute_5[(cse_var_2 + 41)] = 0f32
+ compute_5[(cse_var_2 + 42)] = 0f32
+ compute_5[(cse_var_2 + 43)] = 0f32
+ compute_5[(cse_var_2 + 44)] = 0f32
+ compute_5[(cse_var_2 + 45)] = 0f32
+ compute_5[(cse_var_2 + 46)] = 0f32
+ compute_5[(cse_var_2 + 47)] = 0f32
+ compute_5[(cse_var_2 + 64)] = 0f32
+ compute_5[(cse_var_2 + 65)] = 0f32
+ compute_5[(cse_var_2 + 66)] = 0f32
+ compute_5[(cse_var_2 + 67)] = 0f32
+ compute_5[(cse_var_2 + 68)] = 0f32
+ compute_5[(cse_var_2 + 69)] = 0f32
+ compute_5[(cse_var_2 + 70)] = 0f32
+ compute_5[(cse_var_2 + 71)] = 0f32
+ compute_5[(cse_var_2 + 72)] = 0f32
+ compute_5[(cse_var_2 + 73)] = 0f32
+ compute_5[(cse_var_2 + 74)] = 0f32
+ compute_5[(cse_var_2 + 75)] = 0f32
+ compute_5[(cse_var_2 + 76)] = 0f32
+ compute_5[(cse_var_2 + 77)] = 0f32
+ compute_5[(cse_var_2 + 78)] = 0f32
+ compute_5[(cse_var_2 + 79)] = 0f32
+ compute_5[(cse_var_2 + 96)] = 0f32
+ compute_5[(cse_var_2 + 97)] = 0f32
+ compute_5[(cse_var_2 + 98)] = 0f32
+ compute_5[(cse_var_2 + 99)] = 0f32
+ compute_5[(cse_var_2 + 100)] = 0f32
+ compute_5[(cse_var_2 + 101)] = 0f32
+ compute_5[(cse_var_2 + 102)] = 0f32
+ compute_5[(cse_var_2 + 103)] = 0f32
+ compute_5[(cse_var_2 + 104)] = 0f32
+ compute_5[(cse_var_2 + 105)] = 0f32
+ compute_5[(cse_var_2 + 106)] = 0f32
+ compute_5[(cse_var_2 + 107)] = 0f32
+ compute_5[(cse_var_2 + 108)] = 0f32
+ compute_5[(cse_var_2 + 109)] = 0f32
+ compute_5[(cse_var_2 + 110)] = 0f32
+ compute_5[(cse_var_2 + 111)] = 0f32
+ compute_5[(cse_var_2 + 128)] = 0f32
+ compute_5[(cse_var_2 + 129)] = 0f32
+ compute_5[(cse_var_2 + 130)] = 0f32
+ compute_5[(cse_var_2 + 131)] = 0f32
+ compute_5[(cse_var_2 + 132)] = 0f32
+ compute_5[(cse_var_2 + 133)] = 0f32
+ compute_5[(cse_var_2 + 134)] = 0f32
+ compute_5[(cse_var_2 + 135)] = 0f32
+ compute_5[(cse_var_2 + 136)] = 0f32
+ compute_5[(cse_var_2 + 137)] = 0f32
+ compute_5[(cse_var_2 + 138)] = 0f32
+ compute_5[(cse_var_2 + 139)] = 0f32
+ compute_5[(cse_var_2 + 140)] = 0f32
+ compute_5[(cse_var_2 + 141)] = 0f32
+ compute_5[(cse_var_2 + 142)] = 0f32
+ compute_5[(cse_var_2 + 143)] = 0f32
+ compute_5[(cse_var_2 + 160)] = 0f32
+ compute_5[(cse_var_2 + 161)] = 0f32
+ compute_5[(cse_var_2 + 162)] = 0f32
+ compute_5[(cse_var_2 + 163)] = 0f32
+ compute_5[(cse_var_2 + 164)] = 0f32
+ compute_5[(cse_var_2 + 165)] = 0f32
+ compute_5[(cse_var_2 + 166)] = 0f32
+ compute_5[(cse_var_2 + 167)] = 0f32
+ compute_5[(cse_var_2 + 168)] = 0f32
+ compute_5[(cse_var_2 + 169)] = 0f32
+ compute_5[(cse_var_2 + 170)] = 0f32
+ compute_5[(cse_var_2 + 171)] = 0f32
+ compute_5[(cse_var_2 + 172)] = 0f32
+ compute_5[(cse_var_2 + 173)] = 0f32
+ compute_5[(cse_var_2 + 174)] = 0f32
+ compute_5[(cse_var_2 + 175)] = 0f32
+ compute_5[(cse_var_2 + 192)] = 0f32
+ compute_5[(cse_var_2 + 193)] = 0f32
+ compute_5[(cse_var_2 + 194)] = 0f32
+ compute_5[(cse_var_2 + 195)] = 0f32
+ compute_5[(cse_var_2 + 196)] = 0f32
+ compute_5[(cse_var_2 + 197)] = 0f32
+ compute_5[(cse_var_2 + 198)] = 0f32
+ compute_5[(cse_var_2 + 199)] = 0f32
+ compute_5[(cse_var_2 + 200)] = 0f32
+ compute_5[(cse_var_2 + 201)] = 0f32
+ compute_5[(cse_var_2 + 202)] = 0f32
+ compute_5[(cse_var_2 + 203)] = 0f32
+ compute_5[(cse_var_2 + 204)] = 0f32
+ compute_5[(cse_var_2 + 205)] = 0f32
+ compute_5[(cse_var_2 + 206)] = 0f32
+ compute_5[(cse_var_2 + 207)] = 0f32
+ compute_5[(cse_var_2 + 224)] = 0f32
+ compute_5[(cse_var_2 + 225)] = 0f32
+ compute_5[(cse_var_2 + 226)] = 0f32
+ compute_5[(cse_var_2 + 227)] = 0f32
+ compute_5[(cse_var_2 + 228)] = 0f32
+ compute_5[(cse_var_2 + 229)] = 0f32
+ compute_5[(cse_var_2 + 230)] = 0f32
+ compute_5[(cse_var_2 + 231)] = 0f32
+ compute_5[(cse_var_2 + 232)] = 0f32
+ compute_5[(cse_var_2 + 233)] = 0f32
+ compute_5[(cse_var_2 + 234)] = 0f32
+ compute_5[(cse_var_2 + 235)] = 0f32
+ compute_5[(cse_var_2 + 236)] = 0f32
+ compute_5[(cse_var_2 + 237)] = 0f32
+ compute_5[(cse_var_2 + 238)] = 0f32
+ compute_5[(cse_var_2 + 239)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ let cse_var_131: int32 = (cse_var_2 + 143)
+ let cse_var_130: int32 = (cse_var_2 + 15)
+ let cse_var_129: int32 = (cse_var_2 + 160)
+ let cse_var_128: int32 = (cse_var_2 + 161)
+ let cse_var_127: int32 = (cse_var_2 + 162)
+ let cse_var_126: int32 = (cse_var_2 + 163)
+ let cse_var_125: int32 = (cse_var_2 + 164)
+ let cse_var_124: int32 = (cse_var_2 + 165)
+ let cse_var_123: int32 = (cse_var_2 + 166)
+ let cse_var_122: int32 = (cse_var_2 + 167)
+ let cse_var_121: int32 = (cse_var_2 + 168)
+ let cse_var_120: int32 = (cse_var_2 + 169)
+ let cse_var_119: int32 = (cse_var_2 + 170)
+ let cse_var_118: int32 = (cse_var_2 + 171)
+ let cse_var_117: int32 = (cse_var_2 + 172)
+ let cse_var_116: int32 = (cse_var_2 + 1)
+ let cse_var_115: int32 = (cse_var_2 + 174)
+ let cse_var_114: int32 = (cse_var_2 + 175)
+ let cse_var_113: int32 = (cse_var_2 + 192)
+ let cse_var_112: int32 = (cse_var_2 + 193)
+ let cse_var_111: int32 = (cse_var_2 + 194)
+ let cse_var_110: int32 = (cse_var_2 + 195)
+ let cse_var_109: int32 = (cse_var_2 + 196)
+ let cse_var_108: int32 = (cse_var_2 + 197)
+ let cse_var_107: int32 = (cse_var_2 + 198)
+ let cse_var_106: int32 = (cse_var_2 + 199)
+ let cse_var_105: int32 = (cse_var_2 + 2)
+ let cse_var_104: int32 = (cse_var_2 + 200)
+ let cse_var_103: int32 = (cse_var_2 + 201)
+ let cse_var_102: int32 = (cse_var_2 + 202)
+ let cse_var_101: int32 = (cse_var_2 + 203)
+ let cse_var_100: int32 = (cse_var_2 + 173)
+ let cse_var_99: int32 = (cse_var_2 + 10)
+ let cse_var_98: int32 = (cse_var_2 + 100)
+ let cse_var_97: int32 = (cse_var_2 + 101)
+ let cse_var_96: int32 = (cse_var_2 + 102)
+ let cse_var_95: int32 = (cse_var_2 + 103)
+ let cse_var_94: int32 = (cse_var_2 + 104)
+ let cse_var_93: int32 = (cse_var_2 + 105)
+ let cse_var_92: int32 = (cse_var_2 + 106)
+ let cse_var_91: int32 = (cse_var_2 + 107)
+ let cse_var_90: int32 = (cse_var_2 + 108)
+ let cse_var_89: int32 = (cse_var_2 + 109)
+ let cse_var_88: int32 = (cse_var_2 + 11)
+ let cse_var_87: int32 = (cse_var_2 + 110)
+ let cse_var_86: int32 = (cse_var_2 + 111)
+ let cse_var_85: int32 = (cse_var_2 + 12)
+ let cse_var_84: int32 = (cse_var_2 + 142)
+ let cse_var_83: int32 = (cse_var_2 + 129)
+ let cse_var_82: int32 = (cse_var_2 + 13)
+ let cse_var_81: int32 = (cse_var_2 + 130)
+ let cse_var_80: int32 = (cse_var_2 + 131)
+ let cse_var_79: int32 = (cse_var_2 + 132)
+ let cse_var_78: int32 = (cse_var_2 + 133)
+ let cse_var_77: int32 = (cse_var_2 + 134)
+ let cse_var_76: int32 = (cse_var_2 + 135)
+ let cse_var_75: int32 = (cse_var_2 + 136)
+ let cse_var_74: int32 = (cse_var_2 + 137)
+ let cse_var_73: int32 = (cse_var_2 + 138)
+ let cse_var_72: int32 = (cse_var_2 + 139)
+ let cse_var_71: int32 = (cse_var_2 + 14)
+ let cse_var_70: int32 = (cse_var_2 + 140)
+ let cse_var_69: int32 = (cse_var_2 + 141)
+ let cse_var_68: int32 = (cse_var_2 + 128)
+ let cse_var_67: int32 = (cse_var_2 + 43)
+ let cse_var_66: int32 = (cse_var_2 + 44)
+ let cse_var_65: int32 = (cse_var_2 + 45)
+ let cse_var_64: int32 = (cse_var_2 + 46)
+ let cse_var_63: int32 = (cse_var_2 + 47)
+ let cse_var_62: int32 = (cse_var_2 + 5)
+ let cse_var_61: int32 = (cse_var_2 + 6)
+ let cse_var_60: int32 = (cse_var_2 + 64)
+ let cse_var_59: int32 = (cse_var_2 + 65)
+ let cse_var_58: int32 = (cse_var_2 + 66)
+ let cse_var_57: int32 = (cse_var_2 + 67)
+ let cse_var_56: int32 = (cse_var_2 + 68)
+ let cse_var_55: int32 = (cse_var_2 + 69)
+ let cse_var_54: int32 = (cse_var_2 + 7)
+ let cse_var_53: int32 = (cse_var_2 + 70)
+ let cse_var_52: int32 = (cse_var_2 + 42)
+ let cse_var_51: int32 = (cse_var_2 + 72)
+ let cse_var_50: int32 = (cse_var_2 + 73)
+ let cse_var_49: int32 = (cse_var_2 + 74)
+ let cse_var_48: int32 = (cse_var_2 + 75)
+ let cse_var_47: int32 = (cse_var_2 + 76)
+ let cse_var_46: int32 = (cse_var_2 + 77)
+ let cse_var_45: int32 = (cse_var_2 + 78)
+ let cse_var_44: int32 = (cse_var_2 + 79)
+ let cse_var_43: int32 = (cse_var_2 + 8)
+ let cse_var_42: int32 = (cse_var_2 + 9)
+ let cse_var_41: int32 = (cse_var_2 + 96)
+ let cse_var_40: int32 = (cse_var_2 + 97)
+ let cse_var_39: int32 = (cse_var_2 + 98)
+ let cse_var_38: int32 = (cse_var_2 + 99)
+ let cse_var_37: int32 = (elem_idx*16)
+ let cse_var_36: int32 = (cse_var_2 + 71)
+ let cse_var_35: int32 = (cse_var_2 + 204)
+ let cse_var_34: int32 = (cse_var_2 + 206)
+ let cse_var_33: int32 = (cse_var_2 + 207)
+ let cse_var_32: int32 = (cse_var_2 + 224)
+ let cse_var_31: int32 = (cse_var_2 + 225)
+ let cse_var_30: int32 = (cse_var_2 + 226)
+ let cse_var_29: int32 = (cse_var_2 + 227)
+ let cse_var_28: int32 = (cse_var_2 + 228)
+ let cse_var_27: int32 = (cse_var_2 + 229)
+ let cse_var_26: int32 = (cse_var_2 + 230)
+ let cse_var_25: int32 = (cse_var_2 + 231)
+ let cse_var_24: int32 = (cse_var_2 + 232)
+ let cse_var_23: int32 = (cse_var_2 + 233)
+ let cse_var_22: int32 = (cse_var_2 + 234)
+ let cse_var_21: int32 = (cse_var_2 + 235)
+ let cse_var_20: int32 = (cse_var_2 + 236)
+ let cse_var_19: int32 = (cse_var_2 + 205)
+ let cse_var_18: int32 = (cse_var_2 + 40)
+ let cse_var_17: int32 = (cse_var_2 + 4)
+ let cse_var_16: int32 = (cse_var_2 + 39)
+ let cse_var_15: int32 = (cse_var_2 + 38)
+ let cse_var_14: int32 = (cse_var_2 + 37)
+ let cse_var_13: int32 = (cse_var_2 + 36)
+ let cse_var_12: int32 = (cse_var_2 + 35)
+ let cse_var_11: int32 = (cse_var_2 + 34)
+ let cse_var_10: int32 = (cse_var_2 + 33)
+ let cse_var_9: int32 = (cse_var_2 + 32)
+ let cse_var_8: int32 = (cse_var_2 + 3)
+ let cse_var_7: int32 = (cse_var_2 + 239)
+ let cse_var_6: int32 = (cse_var_2 + 238)
+ let cse_var_5: int32 = (cse_var_2 + 41)
+ let cse_var_4: int32 = (cse_var_2 + 237)
+ let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*2048)
+ {
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_130] = (compute_5[cse_var_130] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_131] = (compute_5[cse_var_131] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_22, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_22, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_132, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -706,7 +1039,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.842 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.721 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 15bee8897..f93abf7cb 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:44.335</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.648</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.459</strong>: <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></li>
-<li><p><strong>00:00.224</strong>: <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></li>
-<li><p><strong>00:00.223</strong>: <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></li>
-<li><p><strong>00:00.221</strong>: <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></li>
-<li><p><strong>00:00.208</strong>: <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></li>
+<li><p><strong>00:43.755</strong>: <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></li>
+<li><p><strong>00:00.235</strong>: <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></li>
+<li><p><strong>00:00.223</strong>: <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></li>
+<li><p><strong>00:00.218</strong>: <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></li>
+<li><p><strong>00:00.216</strong>: <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></li>
</ul>
</div>
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 bac4b20c3..031e7acfb 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 104.05/104.05 result: MeasureResult(costs=(0.0022248586250000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5778279304504395, timestamp=1651278117.4312086) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 6 GFLOPS: 43.38/43.38 result: MeasureResult(costs=(0.005336062894736842,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.565807819366455, timestamp=1651281447.9343586) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/43.38 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
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/104.05 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f015c92afa2
+ 12: 0x00007f2abf079fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 142.22/142.22 result: MeasureResult(costs=(0.001627716564516129,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.128873348236084, timestamp=1651278143.517314) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 144.39/144.39 result: MeasureResult(costs=(0.00160325892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4100971221923828, timestamp=1651281474.2659922) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.001980
+Time cost of this operator: 0.001989
</pre></div>
</div>
<div class="sphx-glr-footer class 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 e99fa7491..651a32e36 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.6 98.738 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.967 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.934 0.294 (1, 1, 10, 10, 3) 1 1
-Total_time - 317.607 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.1 98.716 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.138 0.989 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 0.295 (1, 1, 10, 10, 3) 1 1
+Total_time - 317.174 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.6 96.886 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.702 2.02 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 1.094 (1, 1, 10, 10, 3) 1 1
-Total_time - 84.223 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.05 96.807 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.104 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.089 (1, 1, 10, 10, 3) 1 1
+Total_time - 82.691 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class 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/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 9dd1b4420..24cf3628e 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:44.341</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:43.818</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:40.252</strong>: <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></li>
-<li><p><strong>00:03.481</strong>: <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></li>
-<li><p><strong>00:00.207</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
-<li><p><strong>00:00.203</strong>: <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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
-<li><p><strong>00:00.199</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>00:39.780</strong>: <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></li>
+<li><p><strong>00:03.439</strong>: <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></li>
+<li><p><strong>00:00.204</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>00:00.198</strong>: <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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.197</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
</ul>
</div>
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 1199f6012..ff9772a52 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:08.938</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:08.903</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:06.970</strong>: <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></li>
-<li><p><strong>00:01.744</strong>: <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></li>
-<li><p><strong>00:00.223</strong>: <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></li>
+<li><p><strong>00:07.037</strong>: <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></li>
+<li><p><strong>00:01.660</strong>: <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></li>
+<li><p><strong>00:00.207</strong>: <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></li>
</ul>
</div>
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 09425413e..804cc40d4 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>00:05.652</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.706</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.075</strong>: <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></li>
-<li><p><strong>00:01.149</strong>: <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></li>
-<li><p><strong>00:00.723</strong>: <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></li>
-<li><p><strong>00:00.704</strong>: <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></li>
-<li><p><strong>00:00.306</strong>: <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></li>
-<li><p><strong>00:00.243</strong>: <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></li>
-<li><p><strong>00:00.240</strong>: <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></li>
-<li><p><strong>00:00.213</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:02.112</strong>: <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></li>
+<li><p><strong>00:01.121</strong>: <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></li>
+<li><p><strong>00:00.735</strong>: <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></li>
+<li><p><strong>00:00.725</strong>: <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></li>
+<li><p><strong>00:00.310</strong>: <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></li>
+<li><p><strong>00:00.244</strong>: <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></li>
+<li><p><strong>00:00.236</strong>: <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></li>
+<li><p><strong>00:00.224</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 59ed7f55c..6766b9b77 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -552,7 +552,7 @@ 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/tmp7b7g_5vk/input0.cc'\nsource_filename = \"/tmp/tmp7b7g_5vk/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/tmpw_oz188a/input0.cc'\nsource_filename = \"/tmp/tmpw_oz188a/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 585a1ea2d..d6832861b 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ Can be the a function or the function name.</p></li>
<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">
@@ -1750,7 +1750,7 @@ the initial naive schedule (state).</p>
<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>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 0c7deef98..f3b4de952 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/b772d2727/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 4d4eb8353..fecab58c6 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/b772d2727/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 9885140a4..44af014f9 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/b772d2727/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 fa8ef6fa2..a2dcf6f2e 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/b772d2727/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 ff82257e6..ab10aaff7 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/b772d2727/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 084f24e58..32cd40519 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/b772d2727/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 77fe072db..5ec512507 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/b772d2727/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 2bc819dd8..c651e5b8b 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/b772d2727/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/web/src/runtime.ts#L1134">runtime.ts:1134</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/b772d2727/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 d1d8af74c..4c1d41edc 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/b772d2727/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 328390646..c856d756b 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/b772d2727/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 c0fdff8be..ddb68178a 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/b772d2727/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 3b81b9dac..f56123c96 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/b772d2727/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 04e9144e7..df3de8f8b 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/b772d2727/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 90d114a66..aa6021c17 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/b772d2727/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 75718b3ff..8b4700a7a 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/b772d2727/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 4dbe8c9d9..a04d453e7 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/b772d2727/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 808d245c7..dcdfd6332 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/b772d2727/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 4e09f0a1a..13a34b0c0 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/b772d2727/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 4395123e1..531e64587 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/b772d2727/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 f1e8b5419..4cd3dab3e 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/b772d2727/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 64c1406d9..0f94fd587 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/b772d2727/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/web/src/runtime.ts#L1356">runtime.ts:1356</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/b772d2727/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 9be93d205..667ce8543 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/b772d2727/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 8ff429d64..1763b14a8 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/b772d2727/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 a7ba6f9a8..ce04cb76b 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/b772d2727/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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/b772d2727/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/552f06ed4/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 0e7f6cad4..f68efb613 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 f2126d88d..ff62642c4 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:20.169</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.204</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:19.963</strong>: <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></li>
-<li><p><strong>00:00.206</strong>: <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></li>
+<li><p><strong>00:20.004</strong>: <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></li>
+<li><p><strong>00:00.200</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index e5904ba6d..7d0a2358d 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -539,7 +539,7 @@ 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 21.20s!
+resnet18_v1 inference graph built in 21.30s!
</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 fd6dcb170..573d6050f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -557,7 +557,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 14.73s!
+yolov3-tiny inference graph built in 14.86s!
</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 3c17fec46..b6320d632 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>01:28.387</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:28.154</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:47.136</strong>: <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></li>
-<li><p><strong>00:41.250</strong>: <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></li>
+<li><p><strong>00:46.825</strong>: <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></li>
+<li><p><strong>00:41.329</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 19a1291d7..30e47f90b 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:03.527</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.583</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.978</strong>: <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></li>
-<li><p><strong>00:00.549</strong>: <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></li>
+<li><p><strong>00:03.047</strong>: <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></li>
+<li><p><strong>00:00.536</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index b6a022aff..e20fb8b91 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:00.989</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:01.014</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:00.501</strong>: <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></li>
-<li><p><strong>00:00.488</strong>: <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></li>
+<li><p><strong>00:00.514</strong>: <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></li>
+<li><p><strong>00:00.500</strong>: <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></li>
</ul>
</div>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 2ad5e9b3a..c2253602a 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -545,7 +545,7 @@ operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.608 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 96.593 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 874775fa2..9d5631eda 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -513,7 +513,7 @@ standard deviation.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 494.3400694800004, 'median': 493.9094355999998, 'std': 1.1932189175639154}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 491.7812707299992, 'median': 491.7406261499991, 'std': 0.606950351019823}
</pre></div>
</div>
</div>
@@ -667,129 +667,129 @@ depending on the specifics of the model and the target platform.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 1/25] Current/Best: 23.44/ 23.44 GFLOPS | Progress: (4/10) | 5.13 s
-[Task 1/25] Current/Best: 14.50/ 23.44 GFLOPS | Progress: (8/10) | 7.60 s
-[Task 1/25] Current/Best: 22.82/ 23.56 GFLOPS | Progress: (10/10) | 8.29 s Done.
+[Task 1/25] Current/Best: 3.28/ 14.68 GFLOPS | Progress: (4/10) | 6.66 s
+[Task 1/25] Current/Best: 8.72/ 14.68 GFLOPS | Progress: (8/10) | 10.73 s
+[Task 1/25] Current/Best: 13.92/ 16.88 GFLOPS | Progress: (10/10) | 11.74 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 2/25] Current/Best: 6.77/ 13.80 GFLOPS | Progress: (4/10) | 2.34 s
-[Task 2/25] Current/Best: 17.21/ 17.21 GFLOPS | Progress: (8/10) | 4.05 s
-[Task 2/25] Current/Best: 13.61/ 17.21 GFLOPS | Progress: (10/10) | 4.61 s Done.
+[Task 2/25] Current/Best: 10.15/ 16.52 GFLOPS | Progress: (4/10) | 2.15 s
+[Task 2/25] Current/Best: 12.32/ 16.52 GFLOPS | Progress: (8/10) | 4.11 s
+[Task 2/25] Current/Best: 11.26/ 16.52 GFLOPS | Progress: (10/10) | 4.80 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 3/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (4/10) | 4.32 s
-[Task 3/25] Current/Best: 12.62/ 21.23 GFLOPS | Progress: (8/10) | 6.30 s
-[Task 3/25] Current/Best: 24.13/ 24.13 GFLOPS | Progress: (10/10) | 6.99 s Done.
+[Task 3/25] Current/Best: 13.26/ 13.26 GFLOPS | Progress: (4/10) | 4.88 s
+[Task 3/25] Current/Best: 7.25/ 17.89 GFLOPS | Progress: (8/10) | 7.45 s
+[Task 3/25] Current/Best: 17.52/ 20.39 GFLOPS | Progress: (10/10) | 8.30 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 4/25] Current/Best: 3.46/ 19.08 GFLOPS | Progress: (4/10) | 2.53 s
-[Task 4/25] Current/Best: 11.28/ 19.08 GFLOPS | Progress: (8/10) | 4.53 s
-[Task 4/25] Current/Best: 11.26/ 19.08 GFLOPS | Progress: (10/10) | 6.36 s Done.
+[Task 4/25] Current/Best: 10.97/ 17.60 GFLOPS | Progress: (4/10) | 9.18 s
+[Task 4/25] Current/Best: 15.10/ 17.60 GFLOPS | Progress: (8/10) | 13.24 s
+[Task 4/25] Current/Best: 13.77/ 17.60 GFLOPS | Progress: (10/10) | 14.75 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 5/25] Current/Best: 14.47/ 14.47 GFLOPS | Progress: (4/10) | 3.11 s
-[Task 5/25] Current/Best: 15.45/ 17.47 GFLOPS | Progress: (8/10) | 5.08 s
-[Task 5/25] Current/Best: 13.76/ 17.47 GFLOPS | Progress: (10/10) | 5.87 s Done.
+[Task 5/25] Current/Best: 20.76/ 20.76 GFLOPS | Progress: (4/10) | 2.92 s
+[Task 5/25] Current/Best: 5.81/ 20.76 GFLOPS | Progress: (8/10) | 4.94 s
+[Task 5/25] Current/Best: 4.17/ 20.76 GFLOPS | Progress: (10/10) | 6.28 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 6/25] Current/Best: 11.03/ 14.94 GFLOPS | Progress: (4/10) | 6.11 s
-[Task 6/25] Current/Best: 19.34/ 19.34 GFLOPS | Progress: (8/10) | 8.34 s
-[Task 6/25] Current/Best: 6.36/ 19.34 GFLOPS | Progress: (10/10) | 9.73 s Done.
+[Task 6/25] Current/Best: 13.50/ 19.06 GFLOPS | Progress: (4/10) | 3.47 s
+[Task 6/25] Current/Best: 13.53/ 20.44 GFLOPS | Progress: (8/10) | 5.17 s
+[Task 6/25] Current/Best: 14.25/ 20.44 GFLOPS | Progress: (10/10) | 6.55 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 7/25] Current/Best: 7.84/ 19.00 GFLOPS | Progress: (4/10) | 2.68 s
-[Task 7/25] Current/Best: 7.26/ 19.00 GFLOPS | Progress: (8/10) | 4.44 s
-[Task 7/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (10/10) | 5.90 s Done.
+[Task 7/25] Current/Best: 23.25/ 23.26 GFLOPS | Progress: (4/10) | 3.26 s
+[Task 7/25] Current/Best: 17.09/ 23.26 GFLOPS | Progress: (8/10) | 6.06 s
+[Task 7/25] Current/Best: 16.00/ 23.26 GFLOPS | Progress: (10/10) | 7.01 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 8/25] Current/Best: 9.65/ 13.07 GFLOPS | Progress: (4/10) | 7.57 s
-[Task 8/25] Current/Best: 12.91/ 13.74 GFLOPS | Progress: (8/10) | 9.64 s
-[Task 8/25] Current/Best: 20.11/ 20.11 GFLOPS | Progress: (10/10) | 12.13 s Done.
-
+[Task 8/25] Current/Best: 10.83/ 10.83 GFLOPS | Progress: (4/10) | 4.29 s
+[Task 8/25] Current/Best: 13.19/ 13.19 GFLOPS | Progress: (8/10) | 26.17 s
+[Task 8/25] Current/Best: 11.15/ 13.19 GFLOPS | Progress: (10/10) | 28.21 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 9/25] Current/Best: 14.50/ 23.28 GFLOPS | Progress: (4/10) | 6.34 s
-[Task 9/25] Current/Best: 14.99/ 23.28 GFLOPS | Progress: (8/10) | 9.37 s
-[Task 9/25] Current/Best: 12.19/ 23.28 GFLOPS | Progress: (10/10) | 9.97 s Done.
+[Task 9/25] Current/Best: 15.30/ 15.78 GFLOPS | Progress: (4/10) | 4.48 s
+[Task 9/25] Current/Best: 22.23/ 22.23 GFLOPS | Progress: (8/10) | 9.13 s
+[Task 9/25] Current/Best: 3.53/ 22.23 GFLOPS | Progress: (10/10) | 14.42 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 10/25] Current/Best: 16.39/ 18.13 GFLOPS | Progress: (4/10) | 3.38 s
-[Task 10/25] Current/Best: 19.98/ 19.98 GFLOPS | Progress: (8/10) | 5.05 s
-[Task 10/25] Current/Best: 5.83/ 19.98 GFLOPS | Progress: (10/10) | 6.54 s Done.
+[Task 10/25] Current/Best: 16.32/ 20.37 GFLOPS | Progress: (4/10) | 2.28 s
+[Task 10/25] Current/Best: 14.14/ 20.37 GFLOPS | Progress: (8/10) | 3.89 s
+[Task 10/25] Current/Best: 8.75/ 20.37 GFLOPS | Progress: (10/10) | 4.67 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 11/25] Current/Best: 12.12/ 24.21 GFLOPS | Progress: (4/10) | 2.85 s
-[Task 11/25] Current/Best: 16.83/ 24.21 GFLOPS | Progress: (8/10) | 5.56 s
-[Task 11/25] Current/Best: 7.23/ 24.21 GFLOPS | Progress: (10/10) | 6.70 s Done.
+[Task 11/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (4/10) | 3.19 s
+[Task 11/25] Current/Best: 12.71/ 24.09 GFLOPS | Progress: (8/10) | 5.37 s
+[Task 11/25] Current/Best: 12.90/ 24.09 GFLOPS | Progress: (10/10) | 6.21 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 12/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (4/10) | 4.75 s
-[Task 12/25] Current/Best: 13.98/ 19.66 GFLOPS | Progress: (8/10) | 6.68 s
-[Task 12/25] Current/Best: 17.32/ 19.66 GFLOPS | Progress: (10/10) | 7.57 s Done.
+[Task 12/25] Current/Best: 16.55/ 17.92 GFLOPS | Progress: (4/10) | 3.06 s
+[Task 12/25] Current/Best: 19.06/ 19.06 GFLOPS | Progress: (8/10) | 5.96 s
+[Task 12/25] Current/Best: 10.07/ 19.06 GFLOPS | Progress: (10/10) | 7.36 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 13/25] Current/Best: 9.48/ 18.14 GFLOPS | Progress: (4/10) | 3.81 s
-[Task 13/25] Current/Best: 3.11/ 19.47 GFLOPS | Progress: (8/10) | 6.14 s
-[Task 13/25] Current/Best: 9.63/ 19.47 GFLOPS | Progress: (10/10) | 7.03 s Done.
+[Task 13/25] Current/Best: 6.32/ 20.45 GFLOPS | Progress: (4/10) | 3.13 s
+[Task 13/25] Current/Best: 22.25/ 22.25 GFLOPS | Progress: (8/10) | 5.15 s
+[Task 13/25] Current/Best: 1.56/ 22.25 GFLOPS | Progress: (10/10) | 7.86 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 14/25] Current/Best: 10.01/ 14.25 GFLOPS | Progress: (4/10) | 4.26 s
-[Task 14/25] Current/Best: 5.10/ 16.09 GFLOPS | Progress: (8/10) | 10.27 s
-[Task 14/25] Current/Best: 16.36/ 16.36 GFLOPS | Progress: (10/10) | 11.10 s Done.
-
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 15/25] Current/Best: 9.28/ 21.43 GFLOPS | Progress: (4/10) | 2.19 s
-[Task 15/25] Current/Best: 17.18/ 21.43 GFLOPS | Progress: (8/10) | 7.31 s
-[Task 15/25] Current/Best: 15.30/ 21.43 GFLOPS | Progress: (10/10) | 8.53 s
+[Task 14/25] Current/Best: 19.79/ 19.79 GFLOPS | Progress: (4/10) | 4.77 s
+[Task 14/25] Current/Best: 10.15/ 19.79 GFLOPS | Progress: (8/10) | 7.62 s
+[Task 14/25] Current/Best: 6.64/ 19.79 GFLOPS | Progress: (10/10) | 8.56 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+ Done.
+
+[Task 15/25] Current/Best: 14.37/ 23.79 GFLOPS | Progress: (4/10) | 2.13 s
+[Task 15/25] Current/Best: 6.71/ 23.79 GFLOPS | Progress: (8/10) | 4.35 s
+[Task 15/25] Current/Best: 9.23/ 23.79 GFLOPS | Progress: (10/10) | 9.06 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 16/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (4/10) | 2.69 s
-[Task 16/25] Current/Best: 14.67/ 20.12 GFLOPS | Progress: (8/10) | 4.03 s
-[Task 16/25] Current/Best: 19.88/ 20.12 GFLOPS | Progress: (10/10) | 4.92 s Done.
+[Task 16/25] Current/Best: 3.00/ 19.25 GFLOPS | Progress: (4/10) | 3.21 s
+[Task 16/25] Current/Best: 17.82/ 21.96 GFLOPS | Progress: (8/10) | 4.31 s
+[Task 16/25] Current/Best: 17.75/ 21.96 GFLOPS | Progress: (10/10) | 4.92 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 17/25] Current/Best: 23.86/ 23.86 GFLOPS | Progress: (4/10) | 4.40 s
-[Task 17/25] Current/Best: 12.31/ 23.86 GFLOPS | Progress: (8/10) | 6.21 s
-[Task 17/25] Current/Best: 18.47/ 24.13 GFLOPS | Progress: (10/10) | 7.16 s Done.
+[Task 17/25] Current/Best: 12.31/ 23.47 GFLOPS | Progress: (4/10) | 2.78 s
+[Task 17/25] Current/Best: 17.16/ 23.47 GFLOPS | Progress: (8/10) | 4.84 s
+[Task 17/25] Current/Best: 13.47/ 23.47 GFLOPS | Progress: (10/10) | 5.99 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 18/25] Current/Best: 11.52/ 12.74 GFLOPS | Progress: (4/10) | 4.55 s
-[Task 18/25] Current/Best: 11.94/ 15.86 GFLOPS | Progress: (8/10) | 7.21 s
-[Task 18/25] Current/Best: 11.74/ 22.30 GFLOPS | Progress: (10/10) | 8.66 s Done.
+[Task 18/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/10) | 4.12 s
+[Task 18/25] Current/Best: 8.05/ 18.14 GFLOPS | Progress: (8/10) | 9.30 s
+[Task 18/25] Current/Best: 10.33/ 18.14 GFLOPS | Progress: (10/10) | 11.24 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 19/25] Current/Best: 19.48/ 22.49 GFLOPS | Progress: (4/10) | 4.01 s
-[Task 19/25] Current/Best: 8.63/ 23.03 GFLOPS | Progress: (8/10) | 6.74 s
-[Task 19/25] Current/Best: 18.05/ 23.03 GFLOPS | Progress: (10/10) | 8.17 s Done.
+[Task 19/25] Current/Best: 18.26/ 21.92 GFLOPS | Progress: (4/10) | 3.92 s
+[Task 19/25] Current/Best: 18.20/ 21.92 GFLOPS | Progress: (8/10) | 8.41 s
+[Task 19/25] Current/Best: 12.77/ 21.92 GFLOPS | Progress: (10/10) | 10.57 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 20/25] Current/Best: 9.53/ 16.74 GFLOPS | Progress: (4/10) | 5.32 s
-[Task 20/25] Current/Best: 2.69/ 19.36 GFLOPS | Progress: (8/10) | 7.47 s
-[Task 20/25] Current/Best: 8.93/ 19.36 GFLOPS | Progress: (10/10) | 8.38 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
- Done.
-
-[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (4/10) | 3.31 s
-[Task 21/25] Current/Best: 7.14/ 18.05 GFLOPS | Progress: (8/10) | 5.42 s
-[Task 21/25] Current/Best: 13.11/ 18.05 GFLOPS | Progress: (10/10) | 6.62 s Done.
-
+[Task 20/25] Current/Best: 8.45/ 17.90 GFLOPS | Progress: (4/10) | 3.27 s
+[Task 20/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (8/10) | 5.34 s
+[Task 20/25] Current/Best: 14.25/ 19.01 GFLOPS | Progress: (10/10) | 5.96 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
+[Task 21/25] Current/Best: 5.12/ 17.70 GFLOPS | Progress: (4/10) | 2.87 s
+[Task 21/25] Current/Best: 10.30/ 17.70 GFLOPS | Progress: (8/10) | 4.69 s
+[Task 21/25] Current/Best: 6.99/ 17.70 GFLOPS | Progress: (10/10) | 5.80 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 22/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (4/10) | 2.75 s
-[Task 22/25] Current/Best: 5.29/ 19.72 GFLOPS | Progress: (8/10) | 5.95 s
-[Task 22/25] Current/Best: 9.93/ 19.72 GFLOPS | Progress: (10/10) | 8.20 s Done.
+[Task 22/25] Current/Best: 12.97/ 15.39 GFLOPS | Progress: (4/10) | 3.45 s
+[Task 22/25] Current/Best: 9.93/ 22.09 GFLOPS | Progress: (8/10) | 5.50 s
+[Task 22/25] Current/Best: 5.34/ 22.09 GFLOPS | Progress: (10/10) | 6.39 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 23/25] Current/Best: 16.71/ 20.96 GFLOPS | Progress: (4/10) | 2.71 s
-[Task 23/25] Current/Best: 14.12/ 20.96 GFLOPS | Progress: (8/10) | 4.88 s
-[Task 23/25] Current/Best: 13.48/ 20.96 GFLOPS | Progress: (10/10) | 6.36 s Done.
+[Task 23/25] Current/Best: 14.43/ 17.53 GFLOPS | Progress: (4/10) | 4.35 s
+[Task 23/25] Current/Best: 12.97/ 19.37 GFLOPS | Progress: (8/10) | 6.99 s
+[Task 23/25] Current/Best: 8.89/ 23.59 GFLOPS | Progress: (10/10) | 7.96 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 24/25] Current/Best: 5.46/ 5.87 GFLOPS | Progress: (4/10) | 13.28 s
-[Task 24/25] Current/Best: 2.48/ 10.38 GFLOPS | Progress: (8/10) | 21.36 s
-[Task 24/25] Current/Best: 3.79/ 10.38 GFLOPS | Progress: (10/10) | 22.71 s
+[Task 24/25] Current/Best: 4.30/ 4.30 GFLOPS | Progress: (4/10) | 34.63 s Done.
+ Done.
+ Done.
+
+[Task 24/25] Current/Best: 3.60/ 8.70 GFLOPS | Progress: (8/10) | 56.50 s
+[Task 24/25] Current/Best: 5.20/ 8.70 GFLOPS | Progress: (10/10) | 66.90 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
-[Task 25/25] Current/Best: 5.63/ 5.63 GFLOPS | Progress: (4/10) | 2.09 s
-[Task 25/25] Current/Best: 1.55/ 5.63 GFLOPS | Progress: (8/10) | 33.36 s
-[Task 25/25] Current/Best: 8.97/ 8.97 GFLOPS | Progress: (10/10) | 34.21 s
+[Task 25/25] Current/Best: 5.68/ 9.05 GFLOPS | Progress: (4/10) | 3.54 s
+[Task 25/25] Current/Best: 5.81/ 9.05 GFLOPS | Progress: (8/10) | 6.19 s
+[Task 25/25] Current/Best: 7.64/ 9.05 GFLOPS | Progress: (10/10) | 6.96 s Done.
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -851,8 +851,8 @@ model using optimized operators to speed up our computations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621102
-class='n02123159 tiger cat' with probability=0.356379
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
+class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -890,8 +890,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 417.7892823800016, 'median': 417.7939836500059, 'std': 0.5207584102190087}
-unoptimized: {'mean': 494.3400694800004, 'median': 493.9094355999998, 'std': 1.1932189175639154}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 428.3857485400017, 'median': 428.4126755999978, 'std': 0.6424460229291523}
+unoptimized: {'mean': 491.7812707299992, 'median': 491.7406261499991, 'std': 0.606950351019823}
</pre></div>
</div>
</div>
@@ -905,7 +905,7 @@ 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> ( 6 minutes 59.729 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 49.457 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download 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 51fcf8714..c0d13d682 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -496,7 +496,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.257e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.276e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 8e2662974..c9f326007 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -461,7 +461,7 @@ we can schedule the following series of operations ending with <code class="code
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x2322a160)), stage(b, placeholder(b, 0x232ebc80)), 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=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xe7ae3a0)), stage(b, placeholder(b, 0xe0554d0)), 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=[it [...]
</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 8426f7699..74fd36e8c 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -300,20 +300,20 @@
<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>09:42.321</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>10:41.220</strong> total execution time for <strong>tutorial</strong> files:</p>
<ul class="simple">
-<li><p><strong>06:59.729</strong>: <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></li>
-<li><p><strong>01:00.942</strong>: <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></li>
-<li><p><strong>00:53.033</strong>: <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></li>
-<li><p><strong>00:25.745</strong>: <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></li>
-<li><p><strong>00:20.643</strong>: <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></li>
-<li><p><strong>00:01.153</strong>: <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></li>
-<li><p><strong>00:00.703</strong>: <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></li>
-<li><p><strong>00:00.194</strong>: <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></li>
-<li><p><strong>00:00.055</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
-<li><p><strong>00:00.042</strong>: <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></li>
-<li><p><strong>00:00.042</strong>: <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></li>
-<li><p><strong>00:00.040</strong>: <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></li>
+<li><p><strong>07:49.457</strong>: <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></li>
+<li><p><strong>00:58.813</strong>: <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></li>
+<li><p><strong>00:58.451</strong>: <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></li>
+<li><p><strong>00:26.207</strong>: <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></li>
+<li><p><strong>00:26.040</strong>: <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></li>
+<li><p><strong>00:01.211</strong>: <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></li>
+<li><p><strong>00:00.713</strong>: <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></li>
+<li><p><strong>00:00.199</strong>: <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></li>
+<li><p><strong>00:00.037</strong>: <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></li>
+<li><p><strong>00:00.031</strong>: <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></li>
+<li><p><strong>00:00.030</strong>: <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></li>
+<li><p><strong>00:00.030</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index c26850e56..aa5e20bb7 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -507,7 +507,7 @@ helper function to run a profile of the TVM generated code.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000006
</pre></div>
</div>
@@ -599,7 +599,7 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000024
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -633,10 +633,10 @@ factor to be the number of threads on your CPU.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.137820000229112e-06 1.0
- naive 5.8405e-06 0.7176983516267952
-parallel 6.0809e-06 0.7472394326525774
- vector 2.4667e-05 3.031155763989069
+ numpy 7.180989998687437e-06 1.0
+ naive 6.1019e-06 0.8497296335345577
+parallel 6.112399999999999e-06 0.8511918274663023
+ vector 2.4469599999999997e-05 3.4075524411637703
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -954,7 +954,7 @@ matrix multiplication.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017685
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018402
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -996,7 +996,7 @@ optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.425653
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.253881
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1063,7 +1063,7 @@ schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.299216
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.301795
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1124,7 +1124,7 @@ already cache friendly from our previous optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.334286
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.336453
@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], []),
@@ -1180,7 +1180,7 @@ more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.118259
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.114948
@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], []),
@@ -1257,7 +1257,7 @@ optimized schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109103
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.107904
@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], []),
@@ -1332,7 +1332,7 @@ to `C</cite> when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110817
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110984
@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], []),
@@ -1400,7 +1400,7 @@ of thread-level parallelization.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.143928
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.144506
@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], []),
@@ -1463,13 +1463,13 @@ working, we can compare the results.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4256529191 1.0
- blocking 0.2992160025 0.08734568549887159
- vectorization 0.33428597829999995 0.09758314289114403
-loop permutation 0.1182592719 0.034521673588306635
- array packing 0.10910253610000001 0.03184868364558772
- block caching 0.11081700940000001 0.032349164383271574
- parallelization 0.1439280894 0.04201479040609091
+ none 3.2538812269 1.0
+ blocking 0.30179535830000004 0.09274934678163499
+ vectorization 0.3364530468 0.10340053103921733
+loop permutation 0.11494751169999999 0.03532627766180373
+ array packing 0.1079040546 0.03316164514793955
+ block caching 0.11098448289999999 0.03410833867643529
+ parallelization 0.1445058061 0.044410289135744484
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1501,7 +1501,6 @@ 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 0.942 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download 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>