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 2022/07/26 01:51:17 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@21d54f988056e7e84fdc6504aff683d5c6431266)
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 d1c00186e deploying docs (apache/tvm@21d54f988056e7e84fdc6504aff683d5c6431266)
d1c00186e is described below
commit d1c00186ed05c0e595eb118c23e1b24f4802f0d8
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Jul 26 01:51:12 2022 +0000
deploying docs (apache/tvm@21d54f988056e7e84fdc6504aff683d5c6431266)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1516 ++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 82 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
docs/how_to/compile_models/from_pytorch.html | 5 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 30 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 39 +-
docs/how_to/deploy_models/deploy_prequantized.html | 21 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1516 ++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 82 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 256 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
121 files changed, 3387 insertions(+), 1440 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 57bacfc6e..d2b65c2e2 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.739 seconds)
+ **Total running time of the script:** ( 1 minutes 3.722 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 5cfba086c..868bbd27d 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip297f0f62-371a-4db1-9e3d-15c451a7c233 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip8263c9fb-cde9-4e2b-85c1-086c075c285c 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 601641015..b50a6b498 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 39.8MB/s]
32%|###1 | 13.1M/41.5M [00:00<00:00, 54.3MB/s]
45%|####5 | 18.7M/41.5M [00:00<00:00, 32.1MB/s]
54%|#####4 | 22.6M/41.5M [00:00<00:00, 33.1MB/s]
63%|######3 | 26.3M/41.5M [00:00<00:00, 34.2MB/s]
79%|#######8 | 32.8M/41.5M [00:00<00:00, 42.9MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 44.3MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 55.4MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 52.8MB/s]
47%|####6 | 19.4M/41.5M [00:00<00:00, 45.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 41.0MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 51.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 54.4MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index b86a0ba48..aaf375f1e 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
37%|###7 | 16.6M/44.7M [00:00<00:00, 171MB/s]
94%|#########3| 41.9M/44.7M [00:00<00:00, 226MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 220MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
49%|####9 | 22.0M/44.7M [00:00<00:00, 230MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 262MB/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 9300a462a..968a2842b 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.071 seconds)
+ **Total running time of the script:** ( 1 minutes 2.917 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 58ae8639e..d05b1c3c3 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**04:58.935** total execution time for **how_to_compile_models** files:
+**05:03.235** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.071 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.722 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:01.739 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.917 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.733 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.483 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:26.732 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.777 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.687 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.542 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.134 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.308 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.524 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.364 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.662 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.139 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.277 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.587 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.375 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.396 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index a1805f2b8..9791e1f77 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6078 15.5024 16.3464 15.2047 0.3178
+ 16.0766 16.0816 16.2853 15.8805 0.1172
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 e5ada1244..472ce893a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.62M/170M [00:00<00:04, 37.6MB/s]
4%|4 | 7.21M/170M [00:00<00:04, 36.8MB/s]
7%|7 | 11.9M/170M [00:00<00:03, 42.5MB/s]
11%|#1 | 19.0M/170M [00:00<00:02, 54.5MB/s]
15%|#4 | 25.1M/170M [00:00<00:02, 57.8MB/s]
18%|#8 | 31.3M/170M [00:00<00:02, 60.2MB/s]
22%|##2 | 37.6M/170M [00:00<00:02, 62.1MB/s]
26%|##5 | 43.8M/170M [00:00<00:02, 62.6MB/s]
29%|##9 | 49.7M/170M [00:00<00:02, 50.2MB/s]
33%|###3 | 56.8M/170M [00:01<00:02, 56.4MB/s]
37%|###7 | 63.5M/170M [00:01<00:01, 60.2MB/s]
41%|#### | 69.5M/170M [00:01<00:01, 53.8MB/s]
44%|####4 | 75.0M/170M [00:01<00:02, 46.9MB/s]
47%|####7 | 80.6M/170M [00:01<00:01, 49.8MB/s]
51%|#####1 | 86.9M/170M [00:01<00:01, 54.0MB/s]
55%|#####5 | 93.6M/170M [00:01<00:01, 58.0MB/s]
58%|#####8 | 99.3M/170M [00:01<00:01, 50.5MB/
s]
63%|######2 | 106M/170M [00:02<00:01, 56.0MB/s]
67%|######6 | 113M/170M [00:02<00:00, 60.5MB/s]
70%|####### | 119M/170M [00:02<00:00, 61.2MB/s]
74%|#######3 | 125M/170M [00:02<00:00, 61.0MB/s]
77%|#######7 | 131M/170M [00:02<00:00, 59.5MB/s]
81%|######## | 137M/170M [00:02<00:00, 59.9MB/s]
84%|########4 | 143M/170M [00:02<00:00, 58.5MB/s]
88%|########7 | 149M/170M [00:02<00:00, 61.4MB/s]
91%|#########1| 155M/170M [00:02<00:00, 61.2MB/s]
95%|#########4| 161M/170M [00:03<00:00, 51.2MB/s]
99%|#########8| 167M/170M [00:03<00:00, 54.7MB/s]
100%|##########| 170M/170M [00:03<00:00, 55.7MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
8%|8 | 13.9M/170M [00:00<00:01, 143MB/s]
16%|#6 | 27.6M/170M [00:00<00:01, 126MB/s]
30%|### | 51.2M/170M [00:00<00:00, 178MB/s]
45%|####4 | 76.2M/170M [00:00<00:00, 209MB/s]
58%|#####7 | 98.3M/170M [00:00<00:00, 217MB/s]
72%|#######1 | 121M/170M [00:00<00:00, 226MB/s]
86%|########6 | 147M/170M [00:00<00:00, 238MB/s]
100%|##########| 170M/170M [00:00<00:00, 219MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 51.183 seconds)
+ **Total running time of the script:** ( 3 minutes 2.841 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 7484ba60d..1749b4113 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 183MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
0%| | 40.0k/13.6M [00:00<00:48, 290kB/s]
1%| | 88.0k/13.6M [00:00<00:37, 373kB/s]
2%|1 | 216k/13.6M [00:00<00:20, 687kB/s]
3%|3 | 464k/13.6M [00:00<00:10, 1.28MB/s]
7%|6 | 968k/13.6M [00:00<00:05, 2.48MB/s]
13%|#2 | 1.71M/13.6M [00:00<00:02, 4.20MB/s]
21%|## | 2.82M/13.6M [00:00<00:01, 6.48MB/s]
28%|##7 | 3.78M/13.6M [00:00<00:01, 7.57MB/s]
37%|###6 | 4.97M/13.6M [00:01<00:01, 8.84MB/s]
47%|####7 | 6.39M/13.6M [00:01<00:00, 10.3MB/s]
58%|#####7 | 7.82M/13.6M [00:01<00:00, 11.5MB/s]
67%|######7 | 9.13M/13.6M [00:01<00:00, 12.2MB/s]
76%|#######6 | 10.3M/13.6M [00:01<00:00, 11.9MB/s]
84%|########4 | 11.5M/13.6M [00:01<00:00, 11.7MB/s]
93%|#########2| 12.6M/13.6M [00:01<00:00, 11.4MB/s]
100%|##########| 13.6M/13.6M [00:01<00:00, 8.40MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 89.1310 89.0170 95.4809 88.7248 0.6714
+ 90.3297 90.2381 93.5955 90.1025 0.3959
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.886 seconds)
+ **Total running time of the script:** ( 1 minutes 11.268 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 86f00720e..aa26810b3 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.7911 118.7262 120.8742 117.5458 0.6065
+ 120.7101 120.6807 121.4579 120.0139 0.3205
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 59.647 seconds)
+ **Total running time of the script:** ( 1 minutes 59.003 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 72ccab628..1a40c9ab9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 28.459 seconds)
+ **Total running time of the script:** ( 1 minutes 32.419 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 d40c34c36..3ecce22ee 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6674/132723 [00:00<00:01, 66719.70KB/s]
12%|#1 | 15554/132723 [00:00<00:01, 79702.73KB/s]
18%|#7 | 23525/132723 [00:00<00:01, 58882.74KB/s]
24%|##4 | 32343/132723 [00:00<00:01, 68408.26KB/s]
30%|##9 | 39687/132723 [00:00<00:01, 57331.92KB/s]
37%|###6 | 48452/132723 [00:00<00:01, 65536.92KB/s]
42%|####1 | 55562/132723 [00:00<00:01, 61982.87KB/s]
49%|####8 | 64423/132723 [00:00<00:00, 69140.58KB/s]
54%|#####4 | 72102/132723 [00:01<00:00, 71262.22KB/s]
61%|######1 | 81011/132723 [00:01<00:00, 76323.34KB/s]
67%|######6 | 88892/132723 [00:01<00:00, 63446.95KB/s]
74%|#######3 | 97721/132723 [00:01<00:00, 69742.93KB/s]
79%|#######9 | 105175/132723 [00:01<00:00, 64501.02KB/s]
86%|########5 | 114076/132723 [00:01<00:00, 70781.37KB/s]
92%|#########1| 121533/132723 [00:01<00:00, 67671.94KB/s]
98%|########
#8| 130473/132723 [00:01<00:00, 73433.04KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67940.91KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6047/132723 [00:00<00:02, 60458.67KB/s]
10%|# | 13851/132723 [00:00<00:01, 70789.25KB/s]
16%|#5 | 20930/132723 [00:00<00:02, 38392.67KB/s]
22%|##1 | 28746/132723 [00:00<00:02, 48780.93KB/s]
26%|##6 | 34846/132723 [00:00<00:01, 49733.35KB/s]
32%|###2 | 42737/132723 [00:00<00:01, 57621.30KB/s]
38%|###8 | 50567/132723 [00:00<00:01, 63381.71KB/s]
44%|####4 | 58432/132723 [00:01<00:01, 67726.62KB/s]
49%|####9 | 65663/132723 [00:01<00:01, 66884.73KB/s]
55%|#####5 | 73245/132723 [00:01<00:00, 69435.86KB/s]
61%|######1 | 81281/132723 [00:01<00:00, 72601.27KB/s]
67%|######7 | 89135/132723 [00:01<00:00, 74339.15KB/s]
73%|#######3 | 97001/132723 [00:01<00:00, 75609.88KB/s]
79%|#######9 | 104914/132723 [00:01<00:00, 76650.79KB/s]
85%|########4 | 112774/132723 [00:01<00:00, 77227.12KB/s]
91%|#########
| 120546/132723 [00:01<00:00, 75506.82KB/s]
97%|#########7| 129011/132723 [00:01<00:00, 78189.14KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67463.49KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 28.182 seconds)
+ **Total running time of the script:** ( 2 minutes 32.705 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 4da4838c6..fe269eb64 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
@@ -5,22 +5,22 @@
Computation times
=================
-**10:45.387** total execution time for **how_to_deploy_models** files:
+**11:12.097** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:51.183 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:02.841 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:28.182 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:32.705 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:59.647 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:59.003 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:28.459 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:32.419 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.886 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.268 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.543 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.519 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.481 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.335 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index d32bec5e7..5b2b8bde9 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip06d00bd1-e19f-4a2f-9b79-97c0ffd164f6 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipcc65caf3-e88d-4049-b12f-b94bc5ee1995 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 f6cbc47ae..b68865bdf 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:40.156** total execution time for **how_to_extend_tvm** files:
+**00:40.059** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.067 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:36.917 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.173 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.218 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.909 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.916 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 0cdb98260..cb76a3cab 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6453us [6453us] (45.74%; 45.74%)
- FoldScaleAxis: 7653us [6us] (54.26%; 54.26%)
- FoldConstant: 7648us [1557us] (54.22%; 99.93%)
- InferType: 6091us [6091us] (43.18%; 79.64%)
+ InferType: 6695us [6695us] (45.79%; 45.79%)
+ FoldScaleAxis: 7925us [5us] (54.21%; 54.21%)
+ FoldConstant: 7920us [1593us] (54.17%; 99.93%)
+ InferType: 6327us [6327us] (43.28%; 79.89%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6163us [6163us] (44.77%; 44.77%)
- FoldScaleAxis: 7601us [4us] (55.23%; 55.23%)
- FoldConstant: 7597us [1550us] (55.19%; 99.94%)
- InferType: 6047us [6047us] (43.93%; 79.59%)
+ InferType: 6308us [6308us] (45.02%; 45.02%)
+ FoldScaleAxis: 7705us [5us] (54.98%; 54.98%)
+ FoldConstant: 7700us [1587us] (54.95%; 99.94%)
+ InferType: 6113us [6113us] (43.62%; 79.39%)
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 4256a56fc..ec8dedaac 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.146944 ms
+ Convolution: 54.160442 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 fabf886c0..bbaca8599 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.835711 ms
+ conv2d with tensor core: 9.090662 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 b61f1c57c..c9205ad73 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.017971
- Baseline: 3.371755
+ Numpy running time: 0.018934
+ Baseline: 3.386234
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.301543
+ Opt1: 0.289869
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.334288
+ Opt2: 0.341522
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.111901
+ Opt3: 0.120605
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.115707
+ Opt4: 0.110875
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.109800
+ Opt5: 0.111340
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.142470
+ Opt6: 0.144972
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 0b5692155..883261c5e 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.023** total execution time for **how_to_optimize_operators** files:
+**00:34.419** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.836 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.168 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.220 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.253 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.967 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.997 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index d945911b7..b611d5133 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:06.890** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:54.523** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:15.262 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:11.157 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:20.646 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.967 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.331 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.629 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.411 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.431 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.706 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.821 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.533 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.518 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index c96e42e24..dd6dc2bc2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,11 +240,11 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [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" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -259,150 +259,679 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_2: int32 = (rc.outer.outer*196)
+ let cse_var_1: int32 = (rc.outer.outer*36)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 24), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_1 < 176), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4704), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4928), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5152), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5376), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5600), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5824), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 193536)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6272), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6496)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6496), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6720)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6720), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6944)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6944), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7168), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7392)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7616)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7840)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7840), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8288)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8512)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8512), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8736)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 9184)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 9184), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (yy.outer.inner: int32, 0, 7) {
- let cse_var_3: int32 = ((ff.outer.inner*7) + yy.outer.inner)
- {
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 21)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 39)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 42)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 60)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 66)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 69)]))
- }
- }
- }
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((3 <= threadIdx.x_1) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 16), 27)) && (floormod((threadIdx.x_1 + 16), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 7), 9)) && (floormod((threadIdx.x_1 + 21), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 7), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((threadIdx.x_1 < 14) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 26), 27)) && (floormod((threadIdx.x_1 + 26), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 26), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ if @tir.likely((threadIdx.x_1 < 12), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((threadIdx.x_1 < 9) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + ((floordiv(threadIdx.x_1, 3) + 5)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 16), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 32), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 48), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 64), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 80), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 96), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 128), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 160), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 176), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 192), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 208), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 240), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 256), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 272), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 304), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 320), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 352), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 368), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 384), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 400), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 416), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 464), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 480), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 496), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 512), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 528), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 544), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 592)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 592), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 608), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 624)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 624), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 640), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 656)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 656), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 688)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 688), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 704), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 720)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 736), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 752)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 752), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 768), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 784), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 800), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 816)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 816), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 832), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 848)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 848), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 880)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 880), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 912)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 912), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 928), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 944)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 944), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 960), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 976)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 976), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 992), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1024), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1040)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1040), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1056), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1072)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1072), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1088), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1104)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1104), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1136)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1136), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
for (i1.inner: int32, 0, 2) {
for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((floordiv(blockIdx.x, 7)*32) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -458,7 +987,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.309 ms
+ Execution time of this operator: 0.361 ms
@@ -508,7 +1037,7 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=32)
+ 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_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=7)
@@ -516,26 +1045,26 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_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=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ 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)
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=32)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
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=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -555,14 +1084,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+ 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=16)
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=224)
+ 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=16)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -580,10 +1109,10 @@ 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__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[9216];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -598,97 +1127,598 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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 < 32; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 176) {
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4928) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5152) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5376) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5600) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6272) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6496)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6944)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6944) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7392)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7616) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 7840)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 8288)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8736)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8736) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 9184)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 9184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ pad_temp_shared[((int)threadIdx.x)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 16)] = (((((3 <= ((((int)threadIdx.x) + 16) % 27)) && (((((int)threadIdx.x) + 16) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 16) / 27) * 49)) + ((((((int)threadIdx.x) + 16) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 32) / 27) * 49)) + (((((int)threadIdx.x) + 5) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 48)] = (((((1 <= (((((int)threadIdx.x) / 3) + 7) % 9)) && (((((int)threadIdx.x) + 21) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 48) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 7) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((((int)threadIdx.x) < 14) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 64) / 27) * 49)) + (((((int)threadIdx.x) + 10) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 80)] = (((((3 <= ((((int)threadIdx.x) + 26) % 27)) && (((((int)threadIdx.x) + 26) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 80) / 27) * 49)) + ((((((int)threadIdx.x) + 26) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 12) {
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((((int)threadIdx.x) < 9) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) + 27)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 32) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 48) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 64) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 80) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 96) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 176) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 208) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 240) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 272) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 304) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 368) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 400) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 464) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 496) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 528) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 592)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 592) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 624) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 656)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 656) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 688) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 720)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 752) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 816)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 816) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 848) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 880)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 880) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 912) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 944)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 944) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 976) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1040)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1040) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 1072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1072) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1104)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1104) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1136) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 69)]));
- }
- }
- }
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[((((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -751,7 +1781,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 15.262 seconds)
+ **Total running time of the script:** ( 3 minutes 11.157 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 efb206256..699fb6b85 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8936 9.8868 9.9091 9.8847 0.0110
+ 9.7592 9.7663 9.7725 9.7386 0.0147
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 94477f957..5d488e829 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 766.7095 767.2286 767.6758 765.2240 1.0661
+ 762.3544 762.0270 763.7512 761.2850 1.0331
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.646 seconds)
+ **Total running time of the script:** ( 1 minutes 21.967 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 9b51f47ce..2a130e915 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,79 +397,27 @@ 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_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 128) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[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 (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [4096], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*8192)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.outer.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((i.outer.inner*256) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
+ for (i0.inner: int32, 0, 128) {
for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
}
}
}
@@ -526,7 +474,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.937 ms
+ Execution time of this operator: 2.279 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 407d189a2..5b6b1c830 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:45.028** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.604** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:44.993 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.569 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 4c8e6c2a7..0e0d157a4 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 80.81/80.81 result: MeasureResult(costs=(0.002864772571428571,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5944442749023438, timestamp=1658746666.0119545) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/80.81 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 120.19/120.19 result: MeasureResult(costs=(0.0019261711071428573,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9952189922332764, timestamp=1658794515.151304) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/120.19 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.97/260.97 result: MeasureResult(costs=(0.0008870650442477876,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6255311965942383, timestamp=1658746666.8106744) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 261.18/261.18 result: MeasureResult(costs=(0.0008863828011049723,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4688620567321777, timestamp=1658794516.0824132) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.31/260.97 result: MeasureResult(costs=(0.0436089925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8033726215362549, timestamp=1658746671.290154) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.34/260.97 result: MeasureResult(costs=(0.06939329825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.484875917434692, timestamp=1658746672.5314953) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.29/261.18 result: MeasureResult(costs=(0.043745694,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8309924602508545, timestamp=1658794520.5886626) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/261.18 result: MeasureResult(costs=(0.06941130225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.529698848724365, timestamp=1658794521.8308659) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.15/260.97 result: MeasureResult(costs=(0.008222816928571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.272059440612793, timestamp=1658746683.5780797) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.94/261.18 result: MeasureResult(costs=(0.008284331857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.269599199295044, timestamp=1658794532.8574402) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001254
+ Time cost of this operator: 0.001283
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 5207c57f1..7261f847e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.2 98.719 (1, 2, 10, 10, 3) 2 1 [309.2]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.067 0.979 (1, 6, 10, 10) 1 1 [3.067]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.946 0.302 (1, 1, 10, 10, 3) 1 1 [0.946]
- Total_time - 313.213 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.9 98.71 (1, 2, 10, 10, 3) 2 1 [309.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.078 0.98 (1, 6, 10, 10) 1 1 [3.078]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.309 (1, 1, 10, 10, 3) 1 1 [0.97]
+ Total_time - 313.948 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 76.812 96.608 (1, 6, 10, 10, 1) 2 1 [76.812]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 2.202 (1, 6, 10, 10) 1 1 [1.75]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.947 1.191 (1, 1, 10, 10, 3) 1 1 [0.947]
- Total_time - 79.51 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.438 96.718 (1, 6, 10, 10, 1) 2 1 [80.438]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.766 2.123 (1, 6, 10, 10) 1 1 [1.766]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 1.159 (1, 1, 10, 10, 3) 1 1 [0.964]
+ Total_time - 83.167 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 5ea10b1fc..6822d709d 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpycx4ijhj/images/random'
+ '/tmp/tmpp0m4t4w1/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpycx4ijhj/images/target contains 8144 images
- /tmp/tmpycx4ijhj/images/random contains 5000 images
+ /tmp/tmpp0m4t4w1/images/target contains 8144 images
+ /tmp/tmpp0m4t4w1/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2322 - accuracy: 0.9192 - val_loss: 0.1504 - val_accuracy: 0.9619
+ 328/328 - 55s - loss: 0.2405 - accuracy: 0.9187 - val_loss: 0.1651 - val_accuracy: 0.9468
Epoch 2/3
- 328/328 - 52s - loss: 0.1027 - accuracy: 0.9615 - val_loss: 0.1110 - val_accuracy: 0.9668
+ 328/328 - 52s - loss: 0.1058 - accuracy: 0.9609 - val_loss: 0.1311 - val_accuracy: 0.9573
Epoch 3/3
- 328/328 - 52s - loss: 0.0614 - accuracy: 0.9770 - val_loss: 0.1071 - val_accuracy: 0.9656
+ 328/328 - 52s - loss: 0.0699 - accuracy: 0.9730 - val_loss: 0.1189 - val_accuracy: 0.9619
- <keras.callbacks.History object at 0x7ff59fa19dd0>
+ <keras.callbacks.History object at 0x7f855e3d0110>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 2.353 seconds)
+ **Total running time of the script:** ( 5 minutes 9.984 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 32cb2b565..a335e0603 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
@@ -5,14 +5,14 @@
Computation times
=================
-**05:50.174** total execution time for **how_to_work_with_microtvm** files:
+**05:55.731** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:02.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:09.984 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:44.273 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.489 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.257 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 12b8ffb73..306b4ed7c 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:40.863** total execution time for **how_to_work_with_relay** files:
+**00:42.004** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:29.591 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.456 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.617 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.916 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.649 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.626 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index c7ccc516a..8d342e7fa 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7ff525844d40>
+ <function my_cuda_math_rule at 0x7f8556c6ce60>
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 6f326abf5..d4a2b0492 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:03.963** total execution time for **how_to_work_with_schedules** files:
+**00:04.042** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.847 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.893 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.922 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.516 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.528 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.516 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.095 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.100 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.014 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.015 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 9014158ae..5f689e7ae 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp8v94c34j/input0.cc'\nsource_filename = \"/tmp/tmp8v94c34j/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/tmp1q_31ci7/input0.cc'\nsource_filename = \"/tmp/tmp1q_31ci7/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 b60041654..ec6c1262f 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:20.635** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.061** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.629 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.054 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 64d45efb3..5b5ee93e9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 23.17s!
+ resnet18_v1 inference graph built in 22.58s!
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 01cdc1170..1b170eb7a 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.17s!
+ yolov3-tiny inference graph built in 15.76s!
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 6f95f03a7..b0833e602 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:32.399** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.547** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.875 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.835 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.524 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.713 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index e1bd34e55..570b8bb30 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.248** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.240** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.859 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.850 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.389 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.390 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 36567dccc..9acc024da 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.709** total execution time for **topic_vta_tutorials** files:
+**00:00.698** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.378 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.370 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.331 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.328 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 14ebf471a..5c3102814 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 92.243 ms
+ Execution time of this operator: 93.635 ms
@@ -428,7 +428,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
- .T
+
@@ -444,11 +444,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 10.812 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index ee35ee1e6..e159de6dc 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.04/10.04 result: MeasureResult(costs=(0.026729410599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5596828460693359, timestamp=1658745485.909488) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.58/10.04 result: MeasureResult(costs=(0.1038748416,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8061070442199707, timestamp=1658745487.7333734) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 12.01/12.01 result: MeasureResult(costs=(0.022353895800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5623106956481934, timestamp=1658745488.7816536) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.88/12.01 result: MeasureResult(costs=(0.14290439459999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4103658199310303, timestamp=1658745491.7546768) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.71/12.01 result: MeasureResult(costs=(0.07245006540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2992329597473145, timestamp=1658745493.7000675) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.76/12.01 result: MeasureResult(costs=(0.1525366448,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5984065532684326, timestamp=1658745496.3450274) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/12.01 result: MeasureResult(costs=(0.3089426006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.05877947807312, timestamp=1658745501.4492116) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.92/12.01 result: MeasureResult(costs=(0.0245739802,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5323445796966553, timestamp=1658745502.0052986) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.62/12.01 result: MeasureResult(costs=(0.166102268,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7542853355407715, timestamp=1658745504.8794048) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.55/12.01 result: MeasureResult(costs=(0.10528458119999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.78609037399292, timestamp=1658745506.724965) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.82/9.82 result: MeasureResult(costs=(0.0273374958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.573936939239502, timestamp=1658793316.72432) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.45/9.82 result: MeasureResult(costs=(0.10938282699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9021224975585938, timestamp=1658793318.6384602) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.0227359086,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5595288276672363, timestamp=1658793319.6902707) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.85/11.81 result: MeasureResult(costs=(0.14472830779999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.445192575454712, timestamp=1658793322.7089193) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.64/11.81 result: MeasureResult(costs=(0.07374857180000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.313725233078003, timestamp=1658793324.1500275) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.75/11.81 result: MeasureResult(costs=(0.15324395159999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5731687545776367, timestamp=1658793327.2830582) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.81/11.81 result: MeasureResult(costs=(0.3316435378,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.410801649093628, timestamp=1658793332.7413354) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.07/11.81 result: MeasureResult(costs=(0.026644541800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5688803195953369, timestamp=1658793333.3296034) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.90/11.81 result: MeasureResult(costs=(0.1411162182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3581464290618896, timestamp=1658793335.8070061) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.49/11.81 result: MeasureResult(costs=(0.1076121892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.829699993133545, timestamp=1658793337.6954505) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 880ea680f..63eb7b4e5 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 483.53905445000237, 'median': 483.29701210000167, 'std': 0.7661273699735721}
+ {'mean': 493.9443639300134, 'median': 494.06449910002266, 'std': 1.6148426721759408}
@@ -563,31 +563,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.86/ 17.86 GFLOPS | Progress: (4/20) | 6.61 s
[Task 1/25] Current/Best: 6.26/ 17.86 GFLOPS | Progress: (8/20) | 9.05 s
[Task 1/25] Current/Best: 11.72/ 22.62 GFLOPS | Progress: (12/20) | 11.51 s
[Task 1/25] Current/Best: 17.04/ 23.08 GFLOPS | Progress: (16/20) | 13.18 s
[Task 1/25] Current/Best: 11.71/ 24.21 GFLOPS | Progress: (20/20) | 14.91 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.49/ 13.39 GFLOPS | Progress: (4/20) | 3.85 s
[Task 2/25] Current/Best: 14.00/ 18.91 GFLOPS | Progress: (8/20) | 5.16 s
[Task 2/25] Current/Best: 21.29/ 21.29 GFLOPS | Progress: (12/20) | 6.46 s
[Task 2/25] Current/Best: 12.88/ 21.29 GFLOPS | Progress: (16/20) | 7.71 s
[Task 2/25] Current/Best: 20.26/ 21.29 GFLOPS | Progress: (20/20) | 9.30 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.65/ 10.66 GFLOPS | Progress: (4/20) | 5.78 s
[Task 3/25] Current/Best: 15.79/ 17.14 GFLOPS | Progress: (8/20) | 7.70 s
[Task 3/25] Current/Best: 15.17/ 17.14 GFLOPS | Progress: (12/20) | 9.39 s
[Task 3/25] Current/Best: 7.30/ 24.16 GFLOPS | Progress: (16/20) | 11.29 s
[Task 3/25] Current/Best: 11.73/ 24.16 GFLOPS | Progress: (20/20) | 15.83 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.63/ 20.76 GFLOPS | Progress: (4/20) | 2.34 s
[Task 4/25] Current/Best: 6.97/ 20.76 GFLOPS | Progress: (8/20) | 7.07 s
[Task 4/25] Current/Best: 22.76/ 22.76 GFLOPS | Progress: (12/20) | 12.05 s
[Task 4/25] Current/Best: 17.64/ 22.76 GFLOPS | Progress: (16/20) | 14.46 s
[Task 4/25] Current/Best: 13.51/ 22.76 GFLOPS | Progress: (20/20) | 16.56 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.88/ 10.60 GFLOPS | Progress: (4/20) | 2.54 s
[Task 5/25] Current/Best: 11.91/ 12.89 GFLOPS | Progress: (8/20) | 4.58 s
[Task 5/25] Current/Best: 11.94/ 18.29 GFLOPS | Progress: (12/20) | 7.61 s
[Task 5/25] Current/Best: 11.96/ 23.26 GFLOPS | Progress: (16/20) | 9.05 s
[Task 5/25] Current/Best: 12.19/ 23.26 GFLOPS | Progress: (20/20) | 10.93 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.25/ 21.01 GFLOPS | Progress: (4/20) | 4.08 s
[Task 6/25] Current/Best: 19.28/ 21.01 GFLOPS | Progress: (8/20) | 5.83 s
[Task 6/25] Current/Best: 13.48/ 21.01 GFLOPS | Progress: (12/20) | 7.77 s
[Task 6/25] Current/Best: 20.28/ 21.01 GFLOPS | Progress: (16/20) | 9.99 s
[Task 6/25] Current/Best: 3.76/ 21.01 GFLOPS | Progress: (20/20) | 12.48 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.38/ 13.11 GFLOPS | Progress: (4/20) | 3.60 s
[Task 7/25] Current/Best: 20.53/ 21.39 GFLOPS | Progress: (8/20) | 5.11 s
[Task 7/25] Current/Best: 16.22/ 21.39 GFLOPS | Progress: (12/20) | 7.00 s
[Task 7/25] Current/Best: 12.48/ 21.39 GFLOPS | Progress: (16/20) | 9.02 s
[Task 7/25] Current/Best: 6.48/ 21.94 GFLOPS | Progress: (20/20) | 11.46 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.02/ 14.26 GFLOPS | Progress: (4/20) | 2.90 s
[Task 8/25] Current/Best: 9.31/ 14.26 GFLOPS | Progress: (8/20) | 8.03 s
[Task 8/25] Current/Best: 12.82/ 14.26 GFLOPS | Progress: (12/20) | 14.50 s
[Task 8/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (16/20) | 16.58 s
[Task 8/25] Current/Best: 19.79/ 19.79 GFLOPS | Progress: (20/20) | 23.66 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.56/ 16.02 GFLOPS | Progress: (4/20) | 11.91 s
[Task 9/25] Current/Best: 23.76/ 23.76 GFLOPS | Progress: (8/20) | 13.67 s
[Task 9/25] Current/Best: 8.41/ 23.76 GFLOPS | Progress: (12/20) | 16.19 s
[Task 9/25] Current/Best: 17.99/ 23.76 GFLOPS | Progress: (16/20) | 19.04 s
[Task 9/25] Current/Best: 9.36/ 23.76 GFLOPS | Progress: (20/20) | 27.50 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.49/ 18.49 GFLOPS | Progress: (4/20) | 2.54 s
[Task 10/25] Current/Best: 15.76/ 18.49 GFLOPS | Progress: (8/20) | 4.16 s
[Task 10/25] Current/Best: 12.84/ 19.05 GFLOPS | Progress: (12/20) | 5.69 s
[Task 10/25] Current/Best: 19.13/ 20.62 GFLOPS | Progress: (16/20) | 6.78 s
[Task 10/25] Current/Best: 8.99/ 20.62 GFLOPS | Progress: (20/20
) | 8.29 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.54/ 18.38 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 17.25/ 18.38 GFLOPS | Progress: (8/20) | 6.10 s
[Task 11/25] Current/Best: 18.30/ 18.38 GFLOPS | Progress: (12/20) | 8.17 s
[Task 11/25] Current/Best: 13.59/ 21.57 GFLOPS | Progress: (16/20) | 11.09 s
[Task 11/25] Current/Best: 19.74/ 21.90 GFLOPS | Progress: (20/20) | 13.15 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.93/ 18.25 GFLOPS | Progress: (4/20) | 5.69 s
[Task 12/25] Current/Best: 5.34/ 18.25 GFLOPS | Progress: (8/20) | 9.59 s
[Task 12/25] Current/Best: 19.15/ 19.23 GFLOPS | Progress: (12/20) | 11.54 s
[Task 12/25] Current/Best: 15.70/ 19.23 GFLOPS | Progress: (16/20) | 14.46 s
[Task 12/25] Current/Best: 15.41/ 19.23 GFLOPS | Progress: (20/20) | 16.40 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.84/ 17.62 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 16.30/ 21.45 GFLOPS | Progress: (8/20) | 6.23 s
[Task 13/25] Current/Best: 19.86/ 21.81 GFLOPS | Progress: (12/20) | 9.16 s
[Task 13/25] Current/Best: 12.49/ 21.81 GFLOPS | Progress: (16/20) | 12.57 s
[Task 13/25] Current/Best: 19.22/ 21.81 GFLOPS | Progress: (20/20) | 14.86 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.75/ 13.75 GFLOPS | Progress: (4/20) | 3.28 s
[Task 14/25] Current/Best: 6.20/ 13.75 GFLOPS | Progress: (8/20) | 5.40 s
[Task 14/25] Current/Best: 20.68/ 20.68 GFLOPS | Progress: (12/20) | 8.04 s
[Task 14/25] Current/Best: 17.37/ 20.68 GFLOPS | Progress: (16/20) | 9.65 s Done.
-
[Task 14/25] Current/Best: 17.60/ 20.68 GFLOPS | Progress: (20/20) | 11.34 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.43/ 17.66 GFLOPS | Progress: (4/20) | 2.67 s
[Task 15/25] Current/Best: 14.57/ 18.42 GFLOPS | Progress: (8/20) | 4.01 s
[Task 15/25] Current/Best: 10.55/ 22.60 GFLOPS | Progress: (12/20) | 6.23 s
[Task 15/25] Current/Best: 20.83/ 22.60 GFLOPS | Progress: (16/20) | 9.41 s
[Task 15/25] Current/Best: 9.84/ 22.60 GFLOPS | Progress: (20/20) | 10.41 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.63/ 19.63 GFLOPS | Progress: (4/20) | 2.87 s
[Task 16/25] Current/Best: 3.09/ 19.63 GFLOPS | Progress: (8/20) | 4.47 s
[Task 16/25] Current/Best: 19.69/ 19.69 GFLOPS | Progress: (12/20) | 5.67 s
[Task 16/25] Current/Best: 18.39/ 19.69 GFLOPS | Progress: (16/20) |
7.03 s
[Task 16/25] Current/Best: 10.43/ 22.66 GFLOPS | Progress: (20/20) | 9.16 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.20/ 19.18 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.49/ 23.77 GFLOPS | Progress: (8/20) | 7.53 s
[Task 17/25] Current/Best: 17.11/ 23.77 GFLOPS | Progress: (12/20) | 9.57 s
[Task 17/25] Current/Best: 16.75/ 23.77 GFLOPS | Progress: (16/20) | 11.77 s
[Task 17/25] Current/Best: 10.17/ 23.77 GFLOPS | Progress: (20/20) | 13.92 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.28/ 17.87 GFLOPS | Progress: (4/20) | 3.75 s
[Task 18/25] Current/Best: 10.75/ 19.16 GFLOPS | Progress: (8/20) | 7.45 s
[Task 18/25] Current/Best: 19.46/ 19.46 GFLOPS | Progress: (12/20) | 9.38 s
[Task 18/25] Current/Best: 10.14/ 19.46 GFLOPS | Progress: (16/20) | 13.25 s
[Task 18/25] Current/Best: 20.95/ 20.95 GFLOPS | Progress: (20/20) | 14.73 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.20/ 20.76 GFLOPS | Progress: (4/20) | 5.99 s
[Task 19/25] Current/Best: 2.63/ 20.76 GFLOPS | Progress: (8/20) | 9.32 s
[Task 19/25] Current/Best: 20.23/ 21.95 GFLOPS | Progress: (12/20) | 12.25 s
[Task 19/25] Current/Best: 14.66/ 22.06 GFLOPS | Progress: (16/20) | 15.22 s
[Task 19/25] Current/Best: 2.73/ 23.82 GFLOPS | Progress: (20/20) | 18.01 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.40/ 15.03 GFLOPS | Progress: (4/20) | 3.31 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 6.21 s
[Task 1/25] Current/Best: 6.05/ 17.53 GFLOPS | Progress: (8/20) | 9.14 s
[Task 1/25] Current/Best: 11.55/ 22.65 GFLOPS | Progress: (12/20) | 11.63 s
[Task 1/25] Current/Best: 16.92/ 22.87 GFLOPS | Progress: (16/20) | 13.32 s
[Task 1/25] Current/Best: 11.61/ 23.91 GFLOPS | Progress: (20/20) | 15.05 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.30/ 12.88 GFLOPS | Progress: (4/20) | 3.74 s
[Task 2/25] Current/Best: 14.11/ 17.65 GFLOPS | Progress: (8/20) | 5.06 s
[Task 2/25] Current/Best: 21.11/ 21.11 GFLOPS | Progress: (12/20) | 6.37 s
[Task 2/25] Current/Best: 12.34/ 21.11 GFLOPS | Progress: (16/20) | 7.63 s
[Task 2/25] Current/Best: 19.90/ 21.11 GFLOPS | Progress: (20/20) | 9.23 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.60 GFLOPS | Progress: (4/20) | 5.86 s
[Task 3/25] Current/Best: 15.62/ 16.91 GFLOPS | Progress: (8/20) | 7.77 s
[Task 3/25] Current/Best: 14.90/ 16.91 GFLOPS | Progress: (12/20) | 9.48 s
[Task 3/25] Current/Best: 7.22/ 23.73 GFLOPS | Progress: (16/20) | 11.41 s
[Task 3/25] Current/Best: 12.86/ 23.73 GFLOPS | Progress: (20/20) | 15.95 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.68/ 20.68 GFLOPS | Progress: (4/20) | 2.35 s
[Task 4/25] Current/Best: 6.76/ 20.68 GFLOPS | Progress: (8/20) | 7.13 s
[Task 4/25] Current/Best: 22.03/ 22.03 GFLOPS | Progress: (12/20) | 12.10 s
[Task 4/25] Current/Best: 17.38/ 22.03 GFLOPS | Progress: (16/20) | 14.52 s
[Task 4/25] Current/Best: 13.53/ 22.03 GFLOPS | Progress: (20/20) | 16.48 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.57/ 10.31 GFLOPS | Progress: (4/20) | 2.56 s
[Task 5/25] Current/Best: 11.82/ 12.69 GFLOPS | Progress: (8/20) | 4.63 s
[Task 5/25] Current/Best: 11.92/ 18.08 GFLOPS | Progress: (12/20) | 7.65 s
[Task 5/25] Current/Best: 11.79/ 22.88 GFLOPS | Progress: (16/20) | 9.06 s
[Task 5/25] Current/Best: 12.16/ 22.88 GFLOPS | Progress: (20/20) | 10.94 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.37/ 20.90 GFLOPS | Progress: (4/20) | 4.07 s
[Task 6/25] Current/Best: 19.10/ 20.90 GFLOPS | Progress: (8/20) | 5.84 s
[Task 6/25] Current/Best: 13.43/ 20.90 GFLOPS | Progress: (12/20) | 7.79 s
[Task 6/25] Current/Best: 20.06/ 20.90 GFLOPS | Progress: (16/20) | 10.06 s
[Task 6/25] Current/Best: 3.70/ 20.90 GFLOPS | Progress: (20/20) | 12.62 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.22/ 12.88 GFLOPS | Progress: (4/20) | 3.63 s
[Task 7/25] Current/Best: 20.29/ 21.14 GFLOPS | Progress: (8/20) | 5.15 s
[Task 7/25] Current/Best: 16.19/ 21.14 GFLOPS | Progress: (12/20) | 7.06 s
[Task 7/25] Current/Best: 12.31/ 21.14 GFLOPS | Progress: (16/20) | 9.11 s
[Task 7/25] Current/Best: 6.31/ 21.78 GFLOPS | Progress: (20/20) | 11.57 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.85/ 13.90 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.51/ 13.90 GFLOPS | Progress: (8/20) | 8.12 s
[Task 8/25] Current/Best: 12.51/ 13.90 GFLOPS | Progress: (12/20) | 14.70 s
[Task 8/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (16/20) | 16.83 s
[Task 8/25] Current/Best: 20.14/ 20.14 GFLOPS | Progress: (20/20) | 23.99 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.31/ 15.82 GFLOPS | Progress: (4/20) | 11.95 s
[Task 9/25] Current/Best: 23.40/ 23.40 GFLOPS | Progress: (8/20) | 13.74 s
[Task 9/25] Current/Best: 8.28/ 23.40 GFLOPS | Progress: (12/20) | 16.33 s
[Task 9/25] Current/Best: 17.86/ 23.40 GFLOPS | Progress: (16/20) | 19.23 s
[Task 9/25] Current/Best: 9.06/ 23.40 GFLOPS | Progress: (20/20) | 27.88 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.35/ 18.35 GFLOPS | Progress: (4/20) | 2.60 s
[Task 10/25] Current/Best: 15.50/ 18.35 GFLOPS | Progress: (8/20) | 4.27 s
[Task 10/25] Current/Best: 12.64/ 18.66 GFLOPS | Progress: (12/20) | 5.82 s
[Task 10/25] Current/Best: 19.21/ 20.29 GFLOPS | Progress: (16/20) | 6.93 s
[Task 10/25] Current/Best: 8.92/ 20.29 GFLOPS | Progress: (20/20
) | 8.48 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.17/ 18.13 GFLOPS | Progress: (4/20) | 3.35 s
[Task 11/25] Current/Best: 16.97/ 18.13 GFLOPS | Progress: (8/20) | 6.17 s
[Task 11/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (12/20) | 8.25 s
[Task 11/25] Current/Best: 13.41/ 21.22 GFLOPS | Progress: (16/20) | 11.13 s
[Task 11/25] Current/Best: 19.46/ 21.66 GFLOPS | Progress: (20/20) | 13.21 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.84/ 18.07 GFLOPS | Progress: (4/20) | 5.69 s
[Task 12/25] Current/Best: 5.20/ 18.07 GFLOPS | Progress: (8/20) | 9.67 s
[Task 12/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (12/20) | 11.66 s
[Task 12/25] Current/Best: 15.50/ 18.90 GFLOPS | Progress: (16/20) | 14.59 s
[Task 12/25] Current/Best: 15.10/ 18.90 GFLOPS | Progress: (20/20) | 16.51 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.69/ 17.36 GFLOPS | Progress: (4/20) | 3.76 s
[Task 13/25] Current/Best: 15.69/ 20.98 GFLOPS | Progress: (8/20) | 6.37 s
[Task 13/25] Current/Best: 19.59/ 21.83 GFLOPS | Progress: (12/20) | 9.42 s
[Task 13/25] Current/Best: 12.24/ 21.83 GFLOPS | Progress: (16/20) | 12.88 s
[Task 13/25] Current/Best: 18.70/ 21.83 GFLOPS | Progress: (20/20) | 15.24 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.28/ 13.25 GFLOPS | Progress: (4/20) | 3.43 s
[Task 14/25] Current/Best: 6.12/ 13.34 GFLOPS | Progress: (8/20) | 5.63 s
[Task 14/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (12/20) | 8.35 s
[Task 14/25] Current/Best: 16.75/ 20.32 GFLOPS | Progress: (16/20) | 10.01 s Done.
+
[Task 14/25] Current/Best: 16.98/ 20.32 GFLOPS | Progress: (20/20) | 11.75 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.15/ 17.62 GFLOPS | Progress: (4/20) | 2.75 s
[Task 15/25] Current/Best: 14.51/ 17.98 GFLOPS | Progress: (8/20) | 4.10 s
[Task 15/25] Current/Best: 10.38/ 22.34 GFLOPS | Progress: (12/20) | 6.36 s
[Task 15/25] Current/Best: 20.45/ 22.34 GFLOPS | Progress: (16/20) | 10.05 s
[Task 15/25] Current/Best: 9.70/ 22.34 GFLOPS | Progress: (20/20) | 11.08 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.88/ 20.88 GFLOPS | Progress: (4/20) | 2.96 s
[Task 16/25] Current/Best: 3.04/ 20.88 GFLOPS | Progress: (8/20) | 4.57 s
[Task 16/25] Current/Best: 19.81/ 20.88 GFLOPS | Progress: (12/20) | 5.77 s
[Task 16/25] Current/Best: 18.17/ 20.88 GFLOPS | Progress: (16/20)
| 7.13 s
[Task 16/25] Current/Best: 10.01/ 22.44 GFLOPS | Progress: (20/20) | 9.30 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.27/ 18.76 GFLOPS | Progress: (4/20) | 4.83 s
[Task 17/25] Current/Best: 14.36/ 23.28 GFLOPS | Progress: (8/20) | 7.73 s
[Task 17/25] Current/Best: 17.05/ 23.28 GFLOPS | Progress: (12/20) | 9.79 s
[Task 17/25] Current/Best: 16.52/ 23.28 GFLOPS | Progress: (16/20) | 12.06 s
[Task 17/25] Current/Best: 10.05/ 23.28 GFLOPS | Progress: (20/20) | 14.22 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.44/ 17.91 GFLOPS | Progress: (4/20) | 3.82 s
[Task 18/25] Current/Best: 10.60/ 17.91 GFLOPS | Progress: (8/20) | 7.51 s
[Task 18/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (12/20) | 9.45 s
[Task 18/25] Current/Best: 10.00/ 19.24 GFLOPS | Progress: (16/20) | 13.36 s
[Task 18/25] Current/Best: 20.57/ 20.57 GFLOPS | Progress: (20/20) | 14.87 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.17/ 20.23 GFLOPS | Progress: (4/20) | 6.07 s
[Task 19/25] Current/Best: 2.61/ 20.23 GFLOPS | Progress: (8/20) | 9.44 s
[Task 19/25] Current/Best: 19.93/ 21.69 GFLOPS | Progress: (12/20) | 12.42 s
[Task 19/25] Current/Best: 14.23/ 21.69 GFLOPS | Progress: (16/20) | 15.50 s
[Task 19/25] Current/Best: 2.70/ 23.77 GFLOPS | Progress: (20/20) | 18.32 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.76/ 14.91 GFLOPS | Progress: (4/20) | 3.35 s Done.
Done.
-
[Task 20/25] Current/Best: 10.74/ 15.03 GFLOPS | Progress: (8/20) | 6.78 s
[Task 20/25] Current/Best: 2.35/ 16.60 GFLOPS | Progress: (12/20) | 10.69 s
[Task 20/25] Current/Best: 12.57/ 16.60 GFLOPS | Progress: (16/20) | 14.56 s
[Task 20/25] Current/Best: 12.83/ 22.48 GFLOPS | Progress: (20/20) | 16.63 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.50/ 18.00 GFLOPS | Progress: (4/20) | 3.24 s
[Task 21/25] Current/Best: 14.77/ 18.00 GFLOPS | Progress: (8/20) | 4.85 s
[Task 21/25] Current/Best: 1.63/ 18.00 GFLOPS | Progress: (12/20) | 6.99 s
[Task 21/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 10.50 s
[Task 21/25] Current/Best: 4.47/ 18.28 GFLOPS | Progress: (20/20) | 17.85 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.04 GFLOPS | Progress: (4/20
) | 2.67 s
[Task 22/25] Current/Best: 8.63/ 22.00 GFLOPS | Progress: (8/20) | 4.73 s
[Task 22/25] Current/Best: 20.06/ 22.00 GFLOPS | Progress: (12/20) | 7.09 s
[Task 22/25] Current/Best: 15.36/ 22.00 GFLOPS | Progress: (16/20) | 9.21 s
[Task 22/25] Current/Best: 13.98/ 22.00 GFLOPS | Progress: (20/20) | 10.87 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.53/ 20.90 GFLOPS | Progress: (4/20) | 3.25 s
[Task 23/25] Current/Best: 14.00/ 20.90 GFLOPS | Progress: (8/20) | 6.65 s
[Task 23/25] Current/Best: 20.98/ 21.86 GFLOPS | Progress: (12/20) | 8.51 s
[Task 23/25] Current/Best: 6.39/ 21.86 GFLOPS | Progress: (16/20) | 15.67 s
[Task 23/25] Current/Best: 7.89/ 21.86 GFLOPS | Progress: (20/20) | 19.90 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.40/ 8.40 GFLOPS | Progress: (4/20) | 11.79 s
[Task 24/25] Current/Best: 3.79/ 8.40 GFLOPS | Progress: (8/20) | 23.02 s
[Task 24/25] Current/Best: 4.32/ 8.40 GFLOPS | Progress: (12/20) | 33.78 s Done.
+
[Task 20/25] Current/Best: 9.89/ 14.91 GFLOPS | Progress: (8/20) | 6.75 s
[Task 20/25] Current/Best: 2.32/ 16.42 GFLOPS | Progress: (12/20) | 10.63 s
[Task 20/25] Current/Best: 12.35/ 16.42 GFLOPS | Progress: (16/20) | 14.35 s
[Task 20/25] Current/Best: 12.93/ 22.30 GFLOPS | Progress: (20/20) | 16.46 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.73 GFLOPS | Progress: (4/20) | 3.28 s
[Task 21/25] Current/Best: 14.62/ 17.73 GFLOPS | Progress: (8/20) | 4.89 s
[Task 21/25] Current/Best: 1.61/ 17.73 GFLOPS | Progress: (12/20) | 7.04 s
[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (16/20) | 10.57 s
[Task 21/25] Current/Best: 4.48/ 18.05 GFLOPS | Progress: (20/20) | 17.87 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.04 GFLOPS | Progress: (4/20
) | 2.67 s
[Task 22/25] Current/Best: 8.62/ 22.30 GFLOPS | Progress: (8/20) | 4.71 s
[Task 22/25] Current/Best: 20.34/ 22.30 GFLOPS | Progress: (12/20) | 7.11 s
[Task 22/25] Current/Best: 15.56/ 22.30 GFLOPS | Progress: (16/20) | 9.21 s
[Task 22/25] Current/Best: 14.30/ 22.30 GFLOPS | Progress: (20/20) | 10.93 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.82/ 21.13 GFLOPS | Progress: (4/20) | 3.20 s
[Task 23/25] Current/Best: 14.25/ 21.13 GFLOPS | Progress: (8/20) | 6.57 s
[Task 23/25] Current/Best: 21.22/ 22.12 GFLOPS | Progress: (12/20) | 8.40 s
[Task 23/25] Current/Best: 6.52/ 22.12 GFLOPS | Progress: (16/20) | 15.48 s
[Task 23/25] Current/Best: 7.81/ 22.12 GFLOPS | Progress: (20/20) | 19.66 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.29/ 8.29 GFLOPS | Progress: (4/20) | 11.78 s
[Task 24/25] Current/Best: 3.57/ 8.29 GFLOPS | Progress: (8/20) | 23.00 s
[Task 24/25] Current/Best: 4.38/ 8.29 GFLOPS | Progress: (12/20) | 33.71 s Done.
Done.
-
[Task 24/25] Current/Best: 6.13/ 8.69 GFLOPS | Progress: (16/20) | 39.61 s
[Task 24/25] Current/Best: 3.43/ 8.83 GFLOPS | Progress: (20/20) | 45.53 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.74 GFLOPS | Progress: (4/20) | 11.59 s
[Task 25/25] Current/Best: 5.83/ 8.39 GFLOPS | Progress: (8/20) | 22.85 s
[Task 25/25] Current/Best: 5.92/ 8.39 GFLOPS | Progress: (12/20) | 34.30 s
[Task 25/25] Current/Best: 5.80/ 8.94 GFLOPS | Progress: (16/20) | 36.01 s
[Task 25/25] Current/Best: 2.86/ 9.28 GFLOPS | Progress: (20/20) | 46.72 s
+
[Task 24/25] Current/Best: 5.35/ 8.62 GFLOPS | Progress: (16/20) | 39.46 s
[Task 24/25] Current/Best: 3.39/ 8.62 GFLOPS | Progress: (20/20) | 45.43 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.79 GFLOPS | Progress: (4/20) | 11.59 s
[Task 25/25] Current/Best: 5.67/ 8.01 GFLOPS | Progress: (8/20) | 22.83 s
[Task 25/25] Current/Best: 5.92/ 8.01 GFLOPS | Progress: (12/20) | 34.34 s
[Task 25/25] Current/Best: 5.80/ 8.17 GFLOPS | Progress: (16/20) | 36.08 s
[Task 25/25] Current/Best: 2.83/ 9.32 GFLOPS | Progress: (20/20) | 46.75 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 402.03871841002183, 'median': 401.3822361000166, 'std': 1.676412929443544}
- unoptimized: {'mean': 483.53905445000237, 'median': 483.29701210000167, 'std': 0.7661273699735721}
+ optimized: {'mean': 410.19464660001177, 'median': 409.9865518500337, 'std': 1.479414808980326}
+ unoptimized: {'mean': 493.9443639300134, 'median': 494.06449910002266, 'std': 1.6148426721759408}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 17.447 seconds)
+ **Total running time of the script:** ( 10 minutes 25.169 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 85932b8b7..aecaa266e 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.22e-07 secs/op
+ 1.284e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 459c677c2..9bea6e0ab 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x221e1cf0)), stage(b, placeholder(b, 0x20838b20)), 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, 0x13e630d0)), stage(b, placeholder(b, 0xd1d8140)), 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 994328c70..d30f8d0c9 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:21.588** total execution time for **tutorial** files:
+**13:17.160** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:17.447 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:25.169 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:10.812 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.661 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.514 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:53.974 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:29.292 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.451 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.207 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.524 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.679 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.710 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.494 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.512 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.137 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.152 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 5bf5de987..f23b9944f 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,8 +301,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000006
+ Numpy running time: 0.000009
+ naive: 0.000008
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000007
+ parallel: 0.000006
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.355549998668722e-06 1.0
- naive 6.4793e-06 0.7754486540122838
- parallel 6.7145e-06 0.8035976089030419
- vector 2.45522e-05 2.9384301457009854
+ numpy 8.705270001883036e-06 1.0
+ naive 7.9467e-06 0.9128608300812093
+ parallel 6.057599999999999e-06 0.695854350145335
+ vector 2.4561400000000002e-05 2.821440345295106
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017542
+ Numpy running time: 0.018048
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.254218
+ none: 3.460671
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.299780
+ blocking: 0.304582
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.333285
+ vectorization: 0.341599
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.112729
+ loop permutation: 0.125728
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.108889
+ array packing: 0.109040
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.108695
+ block caching: 0.110982
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.142479
+ parallelization: 0.145363
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2542179431999996 1.0
- blocking 0.2997799901 0.09212044040455834
- vectorization 0.3332848599 0.10241626889078854
- loop permutation 0.1127285375 0.03464074609248501
- array packing 0.10888870320000002 0.03346078999642092
- block caching 0.1086951143 0.03340130138705948
- parallelization 0.1424787447 0.043782791191881595
+ none 3.4606707964999996 1.0
+ blocking 0.3045817251 0.0880123372058513
+ vectorization 0.3415989042 0.09870887012583834
+ loop permutation 0.12572795650000002 0.036330516218750664
+ array packing 0.1090397093 0.03150825828630649
+ block caching 0.11098193730000001 0.03206948705211811
+ parallelization 0.1453633983 0.042004399391879575
@@ -1686,6 +1686,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 1.661 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 9ba077050..ab5126a16 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-75ec1cffa9f160dd3165fedbf4408731ebfa797a
+21d54f988056e7e84fdc6504aff683d5c6431266
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index b66660afe..df4fa474c 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -569,7 +569,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.739 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.722 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 2e70ee830..b7dd72cc1 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip297f0f62-371a-4db1-9e3d-15c451a7c233 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip8263c9fb-cde9-4e2b-85c1-086c075c285c 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 972f0c54e..6c91853e3 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,14 +427,12 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 39.8MB/s]
- 32%|###1 | 13.1M/41.5M [00:00<00:00, 54.3MB/s]
- 45%|####5 | 18.7M/41.5M [00:00<00:00, 32.1MB/s]
- 54%|#####4 | 22.6M/41.5M [00:00<00:00, 33.1MB/s]
- 63%|######3 | 26.3M/41.5M [00:00<00:00, 34.2MB/s]
- 79%|#######8 | 32.8M/41.5M [00:00<00:00, 42.9MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 44.3MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 40.0MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 55.4MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 52.8MB/s]
+ 47%|####6 | 19.4M/41.5M [00:00<00:00, 45.0MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 41.0MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00<00:00, 51.3MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 54.4MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 5efaf9d7f..033d965c3 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,9 +409,8 @@ 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]
- 37%|###7 | 16.6M/44.7M [00:00<00:00, 171MB/s]
- 94%|#########3| 41.9M/44.7M [00:00<00:00, 226MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 220MB/s]
+ 49%|####9 | 22.0M/44.7M [00:00<00:00, 230MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 262MB/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 eef0352f3..f91f8e217 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.071 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.917 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index fb64443d8..ed3d2e766 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:58.935</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:03.235</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -330,44 +330,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:04.071</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:03.722</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:01.739</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:02.917</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:38.733</p></td>
+<td><p>00:40.483</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:26.732</p></td>
+<td><p>00:27.777</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.687</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:24.542</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:24.134</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:24.308</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:21.524</p></td>
+<td><p>00:22.364</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.662</p></td>
+<td><p>00:20.139</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:14.277</p></td>
+<td><p>00:14.587</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.375</p></td>
+<td><p>00:02.396</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index e76cf9895..900e486c3 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6078 15.5024 16.3464 15.2047 0.3178
+ 16.0766 16.0816 16.2853 15.8805 0.1172
</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 5b7a7ce62..b09259fd0 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,35 +431,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|2 | 3.62M/170M [00:00<00:04, 37.6MB/s]
- 4%|4 | 7.21M/170M [00:00<00:04, 36.8MB/s]
- 7%|7 | 11.9M/170M [00:00<00:03, 42.5MB/s]
- 11%|#1 | 19.0M/170M [00:00<00:02, 54.5MB/s]
- 15%|#4 | 25.1M/170M [00:00<00:02, 57.8MB/s]
- 18%|#8 | 31.3M/170M [00:00<00:02, 60.2MB/s]
- 22%|##2 | 37.6M/170M [00:00<00:02, 62.1MB/s]
- 26%|##5 | 43.8M/170M [00:00<00:02, 62.6MB/s]
- 29%|##9 | 49.7M/170M [00:00<00:02, 50.2MB/s]
- 33%|###3 | 56.8M/170M [00:01<00:02, 56.4MB/s]
- 37%|###7 | 63.5M/170M [00:01<00:01, 60.2MB/s]
- 41%|#### | 69.5M/170M [00:01<00:01, 53.8MB/s]
- 44%|####4 | 75.0M/170M [00:01<00:02, 46.9MB/s]
- 47%|####7 | 80.6M/170M [00:01<00:01, 49.8MB/s]
- 51%|#####1 | 86.9M/170M [00:01<00:01, 54.0MB/s]
- 55%|#####5 | 93.6M/170M [00:01<00:01, 58.0MB/s]
- 58%|#####8 | 99.3M/170M [00:01<00:01, 50.5MB/s]
- 63%|######2 | 106M/170M [00:02<00:01, 56.0MB/s]
- 67%|######6 | 113M/170M [00:02<00:00, 60.5MB/s]
- 70%|####### | 119M/170M [00:02<00:00, 61.2MB/s]
- 74%|#######3 | 125M/170M [00:02<00:00, 61.0MB/s]
- 77%|#######7 | 131M/170M [00:02<00:00, 59.5MB/s]
- 81%|######## | 137M/170M [00:02<00:00, 59.9MB/s]
- 84%|########4 | 143M/170M [00:02<00:00, 58.5MB/s]
- 88%|########7 | 149M/170M [00:02<00:00, 61.4MB/s]
- 91%|#########1| 155M/170M [00:02<00:00, 61.2MB/s]
- 95%|#########4| 161M/170M [00:03<00:00, 51.2MB/s]
- 99%|#########8| 167M/170M [00:03<00:00, 54.7MB/s]
-100%|##########| 170M/170M [00:03<00:00, 55.7MB/s]
+ 8%|8 | 13.9M/170M [00:00<00:01, 143MB/s]
+ 16%|#6 | 27.6M/170M [00:00<00:01, 126MB/s]
+ 30%|### | 51.2M/170M [00:00<00:00, 178MB/s]
+ 45%|####4 | 76.2M/170M [00:00<00:00, 209MB/s]
+ 58%|#####7 | 98.3M/170M [00:00<00:00, 217MB/s]
+ 72%|#######1 | 121M/170M [00:00<00:00, 226MB/s]
+ 86%|########6 | 147M/170M [00:00<00:00, 238MB/s]
+100%|##########| 170M/170M [00:00<00:00, 219MB/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').
@@ -554,7 +533,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 51.183 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.841 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 966504063..79f87bee4 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -475,7 +475,22 @@ 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, 183MB/s]
+ 0%| | 40.0k/13.6M [00:00<00:48, 290kB/s]
+ 1%| | 88.0k/13.6M [00:00<00:37, 373kB/s]
+ 2%|1 | 216k/13.6M [00:00<00:20, 687kB/s]
+ 3%|3 | 464k/13.6M [00:00<00:10, 1.28MB/s]
+ 7%|6 | 968k/13.6M [00:00<00:05, 2.48MB/s]
+ 13%|#2 | 1.71M/13.6M [00:00<00:02, 4.20MB/s]
+ 21%|## | 2.82M/13.6M [00:00<00:01, 6.48MB/s]
+ 28%|##7 | 3.78M/13.6M [00:00<00:01, 7.57MB/s]
+ 37%|###6 | 4.97M/13.6M [00:01<00:01, 8.84MB/s]
+ 47%|####7 | 6.39M/13.6M [00:01<00:00, 10.3MB/s]
+ 58%|#####7 | 7.82M/13.6M [00:01<00:00, 11.5MB/s]
+ 67%|######7 | 9.13M/13.6M [00:01<00:00, 12.2MB/s]
+ 76%|#######6 | 10.3M/13.6M [00:01<00:00, 11.9MB/s]
+ 84%|########4 | 11.5M/13.6M [00:01<00:00, 11.7MB/s]
+ 93%|#########2| 12.6M/13.6M [00:01<00:00, 11.4MB/s]
+100%|##########| 13.6M/13.6M [00:01<00:00, 8.40MB/s]
</pre></div>
</div>
</div>
@@ -564,7 +579,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 89.1310 89.0170 95.4809 88.7248 0.6714
+ 90.3297 90.2381 93.5955 90.1025 0.3959
</pre></div>
</div>
<div class="admonition note">
@@ -603,7 +618,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.886 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.268 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 13e49605a..6863dc545 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -568,7 +568,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.7911 118.7262 120.8742 117.5458 0.6065
+ 120.7101 120.6807 121.4579 120.0139 0.3205
</pre></div>
</div>
<div class="admonition note">
@@ -596,7 +596,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 59.647 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 59.003 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 98d799578..2194a0155 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ 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 28.459 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.419 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 547b852bd..c1f16c2f9 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,23 +436,24 @@ 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]
- 5%|5 | 6674/132723 [00:00<00:01, 66719.70KB/s]
- 12%|#1 | 15554/132723 [00:00<00:01, 79702.73KB/s]
- 18%|#7 | 23525/132723 [00:00<00:01, 58882.74KB/s]
- 24%|##4 | 32343/132723 [00:00<00:01, 68408.26KB/s]
- 30%|##9 | 39687/132723 [00:00<00:01, 57331.92KB/s]
- 37%|###6 | 48452/132723 [00:00<00:01, 65536.92KB/s]
- 42%|####1 | 55562/132723 [00:00<00:01, 61982.87KB/s]
- 49%|####8 | 64423/132723 [00:00<00:00, 69140.58KB/s]
- 54%|#####4 | 72102/132723 [00:01<00:00, 71262.22KB/s]
- 61%|######1 | 81011/132723 [00:01<00:00, 76323.34KB/s]
- 67%|######6 | 88892/132723 [00:01<00:00, 63446.95KB/s]
- 74%|#######3 | 97721/132723 [00:01<00:00, 69742.93KB/s]
- 79%|#######9 | 105175/132723 [00:01<00:00, 64501.02KB/s]
- 86%|########5 | 114076/132723 [00:01<00:00, 70781.37KB/s]
- 92%|#########1| 121533/132723 [00:01<00:00, 67671.94KB/s]
- 98%|#########8| 130473/132723 [00:01<00:00, 73433.04KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 67940.91KB/s]
+ 5%|4 | 6047/132723 [00:00<00:02, 60458.67KB/s]
+ 10%|# | 13851/132723 [00:00<00:01, 70789.25KB/s]
+ 16%|#5 | 20930/132723 [00:00<00:02, 38392.67KB/s]
+ 22%|##1 | 28746/132723 [00:00<00:02, 48780.93KB/s]
+ 26%|##6 | 34846/132723 [00:00<00:01, 49733.35KB/s]
+ 32%|###2 | 42737/132723 [00:00<00:01, 57621.30KB/s]
+ 38%|###8 | 50567/132723 [00:00<00:01, 63381.71KB/s]
+ 44%|####4 | 58432/132723 [00:01<00:01, 67726.62KB/s]
+ 49%|####9 | 65663/132723 [00:01<00:01, 66884.73KB/s]
+ 55%|#####5 | 73245/132723 [00:01<00:00, 69435.86KB/s]
+ 61%|######1 | 81281/132723 [00:01<00:00, 72601.27KB/s]
+ 67%|######7 | 89135/132723 [00:01<00:00, 74339.15KB/s]
+ 73%|#######3 | 97001/132723 [00:01<00:00, 75609.88KB/s]
+ 79%|#######9 | 104914/132723 [00:01<00:00, 76650.79KB/s]
+ 85%|########4 | 112774/132723 [00:01<00:00, 77227.12KB/s]
+ 91%|######### | 120546/132723 [00:01<00:00, 75506.82KB/s]
+ 97%|#########7| 129011/132723 [00:01<00:00, 78189.14KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 67463.49KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -495,7 +496,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.182 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.705 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 435cfaa05..af93c675c 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:45.387</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:12.097</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:51.183</p></td>
+<td><p>03:02.841</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:28.182</p></td>
+<td><p>02:32.705</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:59.647</p></td>
+<td><p>01:59.003</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:28.459</p></td>
+<td><p>01:32.419</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:06.886</p></td>
+<td><p>01:11.268</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:28.543</p></td>
+<td><p>00:30.519</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.481</p></td>
+<td><p>00:23.335</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index c3ed65741..eccf23867 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -607,7 +607,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip06d00bd1-e19f-4a2f-9b79-97c0ffd164f6 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.zipcc65caf3-e88d-4049-b12f-b94bc5ee1995 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 70f220b45..3a17cda81 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.156</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.059</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.067</p></td>
+<td><p>00:36.917</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.173</p></td>
+<td><p>00:02.218</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.909</p></td>
+<td><p>00:00.916</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 1acd2d3ee..9bd331e87 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6453us [6453us] (45.74%; 45.74%)
-FoldScaleAxis: 7653us [6us] (54.26%; 54.26%)
- FoldConstant: 7648us [1557us] (54.22%; 99.93%)
- InferType: 6091us [6091us] (43.18%; 79.64%)
+InferType: 6695us [6695us] (45.79%; 45.79%)
+FoldScaleAxis: 7925us [5us] (54.21%; 54.21%)
+ FoldConstant: 7920us [1593us] (54.17%; 99.93%)
+ InferType: 6327us [6327us] (43.28%; 79.89%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6163us [6163us] (44.77%; 44.77%)
-FoldScaleAxis: 7601us [4us] (55.23%; 55.23%)
- FoldConstant: 7597us [1550us] (55.19%; 99.94%)
- InferType: 6047us [6047us] (43.93%; 79.59%)
+InferType: 6308us [6308us] (45.02%; 45.02%)
+FoldScaleAxis: 7705us [5us] (54.98%; 54.98%)
+ FoldConstant: 7700us [1587us] (54.95%; 99.94%)
+ InferType: 6113us [6113us] (43.62%; 79.39%)
</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 18fb625c9..3275ff160 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -559,7 +559,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.146944 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.160442 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 38df4313f..2ee23a6c0 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -901,7 +901,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.835711 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.090662 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 70d23ed26..c61a6909b 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -456,8 +456,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017971
-Baseline: 3.371755
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018934
+Baseline: 3.386234
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -517,7 +517,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301543
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.289869
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -584,7 +584,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.334288
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.341522
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -645,7 +645,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.111901
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120605
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -728,7 +728,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.115707
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110875
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -814,7 +814,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.109800
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111340
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -904,7 +904,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.142470
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144972
</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 79b9ce088..45bd0f09e 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.023</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.419</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.836</p></td>
+<td><p>00:32.168</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.220</p></td>
+<td><p>00:01.253</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:00.967</p></td>
+<td><p>00:00.997</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index 8194f3d1d..e29c8aa38 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:06.890</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:54.523</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:15.262</p></td>
+<td><p>03:11.157</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:20.646</p></td>
+<td><p>01:21.967</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:45.331</p></td>
+<td><p>00:45.629</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:28.411</p></td>
+<td><p>00:18.431</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.706</p></td>
+<td><p>00:08.821</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.533</p></td>
+<td><p>00:08.518</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 4486f49c2..b00e28b01 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
@@ -486,11 +486,11 @@ 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" = 8;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -505,150 +505,679 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_2: int32 = (rc.outer.outer*196)
+ let cse_var_1: int32 = (rc.outer.outer*36)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 24), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_1 < 176), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4704), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 4928), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5152), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5376), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5600), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 5824), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 193536)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6272), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6496)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6496), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6720)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6720), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 6944)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 6944), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7168), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7392)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7616)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 7840)] = kernel[(((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 7840), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8288)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8512)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8512), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8736)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 8960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 9184)] = kernel[((((((blockIdx.x*294912) + (floordiv((threadIdx.x_2 + 9184), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (yy.outer.inner: int32, 0, 7) {
- let cse_var_3: int32 = ((ff.outer.inner*7) + yy.outer.inner)
- {
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 21)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 39)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 42)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 60)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 66)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (yy.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (ff.outer.inner*144)) + (rc.outer.inner*72)) + rx.outer.inner) + 69)]))
- }
- }
- }
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((3 <= threadIdx.x_1) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 16), 27)) && (floormod((threadIdx.x_1 + 16), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 7), 9)) && (floormod((threadIdx.x_1 + 21), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 7), 9)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((threadIdx.x_1 < 14) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 26), 27)) && (floormod((threadIdx.x_1 + 26), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 26), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ if @tir.likely((threadIdx.x_1 < 12), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((threadIdx.x_1 < 9) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + ((floordiv(threadIdx.x_1, 3) + 5)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 16), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 32), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 48), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 64), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 80), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 96), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 128), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 160), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 176), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 192), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 208), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 240), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 256), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 272), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 304), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 320), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 352), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 368), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 384), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 400), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 416), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 464), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 480), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 496), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 512), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 528), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 544), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 592)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 592), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 608), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 624)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 624), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 640), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 656)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 656), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 688)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 688), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 704), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 720)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 736), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 752)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 752), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 768), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 784), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 800), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 816)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 816), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 832), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 848)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 848), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 880)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 880), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 912)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 912), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 928), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 944)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 944), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 960), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 976)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 976), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 992), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1024), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1040)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1040), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1056), 36)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1072)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1072), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1088), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1104)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1104), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1136)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1136), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
for (i1.inner: int32, 0, 2) {
for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*3136) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*64) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((floordiv(blockIdx.x, 7)*32) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -686,7 +1215,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.309 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.361 ms
</pre></div>
</div>
</div>
@@ -717,7 +1246,7 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
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=32)
+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_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=7)
@@ -725,26 +1254,26 @@ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_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=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+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)
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=32)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
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=7)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -764,14 +1293,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+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=16)
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=224)
+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=16)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -789,10 +1318,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[9216];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -807,97 +1336,598 @@ extern "C" __global__ void __launch_bounds__(224) default_function_ker
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 < 32; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 176) {
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4928) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5152) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5376) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5600) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6272) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6496)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6944)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6944) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7392)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7616) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 7840)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 8288)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8736)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8736) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 9184)] = kernel[((((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 9184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ pad_temp_shared[((int)threadIdx.x)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 16)] = (((((3 <= ((((int)threadIdx.x) + 16) % 27)) && (((((int)threadIdx.x) + 16) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 16) / 27) * 49)) + ((((((int)threadIdx.x) + 16) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 32) / 27) * 49)) + (((((int)threadIdx.x) + 5) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 48)] = (((((1 <= (((((int)threadIdx.x) / 3) + 7) % 9)) && (((((int)threadIdx.x) + 21) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 48) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 7) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((((int)threadIdx.x) < 14) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 64) / 27) * 49)) + (((((int)threadIdx.x) + 10) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 80)] = (((((3 <= ((((int)threadIdx.x) + 26) % 27)) && (((((int)threadIdx.x) + 26) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 80) / 27) * 49)) + ((((((int)threadIdx.x) + 26) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) [...]
+ if (((int)threadIdx.x) < 12) {
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((((int)threadIdx.x) < 9) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) + 27)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 32) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 48) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 64) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 80) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 96) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 176) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 208) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 240) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 272) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 304) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 368) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 400) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 464) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 496) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 528) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 592)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 592) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 624) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 656)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 656) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 688) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 720)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 752) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 816)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 816) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 848) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 880)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 880) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 912) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 944)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 944) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 976) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1040)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1040) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 36) * 4608)) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 1072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1072) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1104)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1104) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1136) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 12)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 15)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 18)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 21)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 24)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 27)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 30)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 33)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 36)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 39)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 42)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 45)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 48)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 51)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 54)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 57)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 60)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 63)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 66)]));
- conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] = (conv2d_nchw[((ff_outer_inner * 7) + yy_outer_inner)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (yy_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (ff_outer_inner * 144)) + (rc_outer_inner * 72)) + rx_outer_inner) + 69)]));
- }
- }
- }
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[((((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -935,7 +1965,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 15.262 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 11.157 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index f427d4c0c..5c879ff7f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8936 9.8868 9.9091 9.8847 0.0110
+ 9.7592 9.7663 9.7725 9.7386 0.0147
</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 27abac807..74d522300 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ 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)
- 766.7095 767.2286 767.6758 765.2240 1.0661
+ 762.3544 762.0270 763.7512 761.2850 1.0331
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ 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 20.646 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.967 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 344347522..dbb411752 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,79 +620,27 @@ 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_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 128) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[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 (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [4096], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*8192)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.outer.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((i.outer.inner*256) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
+ for (i0.inner: int32, 0, 128) {
for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
}
}
}
@@ -731,7 +679,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.937 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.279 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 3d7ccb5bd..ed98d8878 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.028</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.604</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:44.993</p></td>
+<td><p>00:45.569</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.019</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
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 39090d82e..e02413f1c 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1431,8 +1431,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 80.81/80.81 result: MeasureResult(costs=(0.002864772571428571,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5944442749023438, timestamp=1658746666.0119545) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/80.81 result: Traceback (most recent call last):
+No: 9 GFLOPS: 120.19/120.19 result: MeasureResult(costs=(0.0019261711071428573,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9952189922332764, timestamp=1658794515.151304) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/120.19 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1555,8 +1555,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.97/260.97 result: MeasureResult(costs=(0.0008870650442477876,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6255311965942383, timestamp=1658746666.8106744) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 11 GFLOPS: 261.18/261.18 result: MeasureResult(costs=(0.0008863828011049723,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4688620567321777, timestamp=1658794516.0824132) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1679,7 +1679,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1802,7 +1802,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1925,9 +1925,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.31/260.97 result: MeasureResult(costs=(0.0436089925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8033726215362549, timestamp=1658746671.290154) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.34/260.97 result: MeasureResult(costs=(0.06939329825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.484875917434692, timestamp=1658746672.5314953) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.29/261.18 result: MeasureResult(costs=(0.043745694,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8309924602508545, timestamp=1658794520.5886626) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/261.18 result: MeasureResult(costs=(0.06941130225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.529698848724365, timestamp=1658794521.8308659) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/261.18 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
@@ -1945,8 +1945,8 @@ No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.15/260.97 result: MeasureResult(costs=(0.008222816928571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.272059440612793, timestamp=1658746683.5780797) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.94/261.18 result: MeasureResult(costs=(0.008284331857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.269599199295044, timestamp=1658794532.8574402) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2069,7 +2069,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/261.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2232,7 +2232,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001254
+Time cost of this operator: 0.001283
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index c0abbbba3..34eade602 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.2 98.719 (1, 2, 10, 10, 3) 2 1 [309.2]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.067 0.979 (1, 6, 10, 10) 1 1 [3.067]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.946 0.302 (1, 1, 10, 10, 3) 1 1 [0.946]
-Total_time - 313.213 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.9 98.71 (1, 2, 10, 10, 3) 2 1 [309.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.078 0.98 (1, 6, 10, 10) 1 1 [3.078]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.309 (1, 1, 10, 10, 3) 1 1 [0.97]
+Total_time - 313.948 - - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 76.812 96.608 (1, 6, 10, 10, 1) 2 1 [76.812]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 2.202 (1, 6, 10, 10) 1 1 [1.75]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.947 1.191 (1, 1, 10, 10, 3) 1 1 [0.947]
-Total_time - 79.51 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.438 96.718 (1, 6, 10, 10, 1) 2 1 [80.438]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.766 2.123 (1, 6, 10, 10) 1 1 [1.766]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 1.159 (1, 1, 10, 10, 3) 1 1 [0.964]
+Total_time - 83.167 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index a0d7975cc..a3d184c86 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpycx4ijhj/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpp0m4t4w1/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpycx4ijhj/images/target contains 8144 images
-/tmp/tmpycx4ijhj/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpp0m4t4w1/images/target contains 8144 images
+/tmp/tmpp0m4t4w1/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2322 - accuracy: 0.9192 - val_loss: 0.1504 - val_accuracy: 0.9619
+328/328 - 55s - loss: 0.2405 - accuracy: 0.9187 - val_loss: 0.1651 - val_accuracy: 0.9468
Epoch 2/3
-328/328 - 52s - loss: 0.1027 - accuracy: 0.9615 - val_loss: 0.1110 - val_accuracy: 0.9668
+328/328 - 52s - loss: 0.1058 - accuracy: 0.9609 - val_loss: 0.1311 - val_accuracy: 0.9573
Epoch 3/3
-328/328 - 52s - loss: 0.0614 - accuracy: 0.9770 - val_loss: 0.1071 - val_accuracy: 0.9656
+328/328 - 52s - loss: 0.0699 - accuracy: 0.9730 - val_loss: 0.1189 - val_accuracy: 0.9619
-<keras.callbacks.History object at 0x7ff59fa19dd0>
+<keras.callbacks.History object at 0x7f855e3d0110>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 2.353 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 9.984 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index f18803c6b..cf7aba526 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:50.174</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:55.731</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:02.353</p></td>
+<td><p>05:09.984</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:44.273</p></td>
+<td><p>00:42.489</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.546</p></td>
+<td><p>00:03.257</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
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 78c2f15c9..2a80f4cef 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.863</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.004</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:29.591</p></td>
+<td><p>00:30.456</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.617</p></td>
+<td><p>00:09.916</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.649</p></td>
+<td><p>00:01.626</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 70c666f61..12504f571 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -517,7 +517,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7ff525844d40>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f8556c6ce60>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index c3b1dc69e..47dabba17 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.963</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.042</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,35 +331,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.847</p></td>
+<td><p>00:01.893</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.924</p></td>
+<td><p>00:00.922</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.516</p></td>
+<td><p>00:00.528</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.500</p></td>
+<td><p>00:00.516</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.095</p></td>
+<td><p>00:00.100</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.040</p></td>
+<td><p>00:00.041</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.026</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.014</p></td>
+<td><p>00:00.015</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 00e42effa..39b0af49a 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -572,7 +572,7 @@ 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/tmp8v94c34j/input0.cc'\nsource_filename = \"/tmp/tmp8v94c34j/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/tmp1q_31ci7/input0.cc'\nsource_filename = \"/tmp/tmp1q_31ci7/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 555f5e519..9db5b9de9 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1597,7 +1597,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1881,7 +1881,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 3bf0031bb..f2d99cd95 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/75ec1cffa/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 b8003f1d1..6e058bbd0 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/75ec1cffa/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 e9157fb69..5e9b054f6 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/75ec1cffa/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 f2fae0d93..19217c51c 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/75ec1cffa/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 e16ef5cdb..aeb67469b 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/75ec1cffa/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 caabb6040..d12c0b535 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/75ec1cffa/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 a268ba0f3..ee1001423 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/75ec1cffa/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 f776227b7..a4905b973 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/75ec1cffa/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/75ec1cffa/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 c381318bb..68aed0999 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/75ec1cffa/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 a8de6f5db..a857822e6 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/75ec1cffa/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 70954e9ea..4a02a617f 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/75ec1cffa/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 c676056e8..30d4b3231 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/75ec1cffa/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 9748f7795..7063fb528 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/75ec1cffa/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 9e8f6741f..0281f602b 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/75ec1cffa/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 b573c656a..aea1c3cc5 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/75ec1cffa/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 6097b9849..79f189ee5 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/75ec1cffa/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 c1cd4a1ce..909d4e6aa 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/75ec1cffa/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 38b4b074b..1c22b2582 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/75ec1cffa/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 93be523bb..e2b5ed330 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/75ec1cffa/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 de87e4ac0..92644c1dd 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/75ec1cffa/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 a07fe75d6..01e7e11bd 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/75ec1cffa/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/75ec1cffa/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 b9cc7d836..a52c44a85 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/75ec1cffa/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 05cdf2675..2cbcb7762 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/75ec1cffa/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 e4f69429f..467c8af2b 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/75ec1cffa/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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/75ec1cffa/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/21d54f988/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 b666f8894..88105698d 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 d30424946..66a5116ce 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.635</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.061</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -331,7 +331,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:20.629</p></td>
+<td><p>00:21.054</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 52e7faa11..26bc4a9f9 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 23.17s!
+resnet18_v1 inference graph built in 22.58s!
</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 1ad461a3e..e6be81312 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.17s!
+yolov3-tiny inference graph built in 15.76s!
</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 300ee6a57..869f12573 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:32.399</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.547</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.875</p></td>
+<td><p>00:48.835</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:43.524</p></td>
+<td><p>00:42.713</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 8f77684a9..f8ab19447 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.248</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.240</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.859</p></td>
+<td><p>00:02.850</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.389</p></td>
+<td><p>00:00.390</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index b36c20cc0..23ba81d9f 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.709</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.698</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.378</p></td>
+<td><p>00:00.370</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.331</p></td>
+<td><p>00:00.328</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 2d29358b0..d32418a8a 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -561,7 +561,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 92.243 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.635 ms
</pre></div>
</div>
</div>
@@ -625,7 +625,6 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-.T
</pre></div>
</div>
</div>
@@ -636,7 +635,6 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.812 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_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">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index c903fce52..416e9afc0 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -663,16 +663,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.04/10.04 result: MeasureResult(costs=(0.026729410599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5596828460693359, timestamp=1658745485.909488) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.58/10.04 result: MeasureResult(costs=(0.1038748416,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8061070442199707, timestamp=1658745487.7333734) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 12.01/12.01 result: MeasureResult(costs=(0.022353895800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5623106956481934, timestamp=1658745488.7816536) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.88/12.01 result: MeasureResult(costs=(0.14290439459999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4103658199310303, timestamp=1658745491.7546768) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.71/12.01 result: MeasureResult(costs=(0.07245006540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2992329597473145, timestamp=1658745493.7000675) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.76/12.01 result: MeasureResult(costs=(0.1525366448,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5984065532684326, timestamp=1658745496.3450274) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/12.01 result: MeasureResult(costs=(0.3089426006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.05877947807312, timestamp=1658745501.4492116) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.92/12.01 result: MeasureResult(costs=(0.0245739802,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5323445796966553, timestamp=1658745502.0052986) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.62/12.01 result: MeasureResult(costs=(0.166102268,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7542853355407715, timestamp=1658745504.8794048) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.55/12.01 result: MeasureResult(costs=(0.10528458119999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.78609037399292, timestamp=1658745506.724965) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.82/9.82 result: MeasureResult(costs=(0.0273374958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.573936939239502, timestamp=1658793316.72432) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.45/9.82 result: MeasureResult(costs=(0.10938282699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9021224975585938, timestamp=1658793318.6384602) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.0227359086,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5595288276672363, timestamp=1658793319.6902707) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.85/11.81 result: MeasureResult(costs=(0.14472830779999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.445192575454712, timestamp=1658793322.7089193) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.64/11.81 result: MeasureResult(costs=(0.07374857180000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.313725233078003, timestamp=1658793324.1500275) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.75/11.81 result: MeasureResult(costs=(0.15324395159999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5731687545776367, timestamp=1658793327.2830582) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.81/11.81 result: MeasureResult(costs=(0.3316435378,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.410801649093628, timestamp=1658793332.7413354) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.07/11.81 result: MeasureResult(costs=(0.026644541800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5688803195953369, timestamp=1658793333.3296034) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.90/11.81 result: MeasureResult(costs=(0.1411162182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3581464290618896, timestamp=1658793335.8070061) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.49/11.81 result: MeasureResult(costs=(0.1076121892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.829699993133545, timestamp=1658793337.6954505) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 4b61ec0e0..b7bcc8571 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -545,7 +545,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 483.53905445000237, 'median': 483.29701210000167, 'std': 0.7661273699735721}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.9443639300134, 'median': 494.06449910002266, 'std': 1.6148426721759408}
</pre></div>
</div>
</div>
@@ -700,179 +700,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.86/ 17.86 GFLOPS | Progress: (4/20) | 6.61 s
-[Task 1/25] Current/Best: 6.26/ 17.86 GFLOPS | Progress: (8/20) | 9.05 s
-[Task 1/25] Current/Best: 11.72/ 22.62 GFLOPS | Progress: (12/20) | 11.51 s
-[Task 1/25] Current/Best: 17.04/ 23.08 GFLOPS | Progress: (16/20) | 13.18 s
-[Task 1/25] Current/Best: 11.71/ 24.21 GFLOPS | Progress: (20/20) | 14.91 s Done.
+[Task 1/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 6.21 s
+[Task 1/25] Current/Best: 6.05/ 17.53 GFLOPS | Progress: (8/20) | 9.14 s
+[Task 1/25] Current/Best: 11.55/ 22.65 GFLOPS | Progress: (12/20) | 11.63 s
+[Task 1/25] Current/Best: 16.92/ 22.87 GFLOPS | Progress: (16/20) | 13.32 s
+[Task 1/25] Current/Best: 11.61/ 23.91 GFLOPS | Progress: (20/20) | 15.05 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.49/ 13.39 GFLOPS | Progress: (4/20) | 3.85 s
-[Task 2/25] Current/Best: 14.00/ 18.91 GFLOPS | Progress: (8/20) | 5.16 s
-[Task 2/25] Current/Best: 21.29/ 21.29 GFLOPS | Progress: (12/20) | 6.46 s
-[Task 2/25] Current/Best: 12.88/ 21.29 GFLOPS | Progress: (16/20) | 7.71 s
-[Task 2/25] Current/Best: 20.26/ 21.29 GFLOPS | Progress: (20/20) | 9.30 s Done.
+[Task 2/25] Current/Best: 12.30/ 12.88 GFLOPS | Progress: (4/20) | 3.74 s
+[Task 2/25] Current/Best: 14.11/ 17.65 GFLOPS | Progress: (8/20) | 5.06 s
+[Task 2/25] Current/Best: 21.11/ 21.11 GFLOPS | Progress: (12/20) | 6.37 s
+[Task 2/25] Current/Best: 12.34/ 21.11 GFLOPS | Progress: (16/20) | 7.63 s
+[Task 2/25] Current/Best: 19.90/ 21.11 GFLOPS | Progress: (20/20) | 9.23 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.65/ 10.66 GFLOPS | Progress: (4/20) | 5.78 s
-[Task 3/25] Current/Best: 15.79/ 17.14 GFLOPS | Progress: (8/20) | 7.70 s
-[Task 3/25] Current/Best: 15.17/ 17.14 GFLOPS | Progress: (12/20) | 9.39 s
-[Task 3/25] Current/Best: 7.30/ 24.16 GFLOPS | Progress: (16/20) | 11.29 s
-[Task 3/25] Current/Best: 11.73/ 24.16 GFLOPS | Progress: (20/20) | 15.83 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.60 GFLOPS | Progress: (4/20) | 5.86 s
+[Task 3/25] Current/Best: 15.62/ 16.91 GFLOPS | Progress: (8/20) | 7.77 s
+[Task 3/25] Current/Best: 14.90/ 16.91 GFLOPS | Progress: (12/20) | 9.48 s
+[Task 3/25] Current/Best: 7.22/ 23.73 GFLOPS | Progress: (16/20) | 11.41 s
+[Task 3/25] Current/Best: 12.86/ 23.73 GFLOPS | Progress: (20/20) | 15.95 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.63/ 20.76 GFLOPS | Progress: (4/20) | 2.34 s
-[Task 4/25] Current/Best: 6.97/ 20.76 GFLOPS | Progress: (8/20) | 7.07 s
-[Task 4/25] Current/Best: 22.76/ 22.76 GFLOPS | Progress: (12/20) | 12.05 s
-[Task 4/25] Current/Best: 17.64/ 22.76 GFLOPS | Progress: (16/20) | 14.46 s
-[Task 4/25] Current/Best: 13.51/ 22.76 GFLOPS | Progress: (20/20) | 16.56 s Done.
+[Task 4/25] Current/Best: 9.68/ 20.68 GFLOPS | Progress: (4/20) | 2.35 s
+[Task 4/25] Current/Best: 6.76/ 20.68 GFLOPS | Progress: (8/20) | 7.13 s
+[Task 4/25] Current/Best: 22.03/ 22.03 GFLOPS | Progress: (12/20) | 12.10 s
+[Task 4/25] Current/Best: 17.38/ 22.03 GFLOPS | Progress: (16/20) | 14.52 s
+[Task 4/25] Current/Best: 13.53/ 22.03 GFLOPS | Progress: (20/20) | 16.48 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.88/ 10.60 GFLOPS | Progress: (4/20) | 2.54 s
-[Task 5/25] Current/Best: 11.91/ 12.89 GFLOPS | Progress: (8/20) | 4.58 s
-[Task 5/25] Current/Best: 11.94/ 18.29 GFLOPS | Progress: (12/20) | 7.61 s
-[Task 5/25] Current/Best: 11.96/ 23.26 GFLOPS | Progress: (16/20) | 9.05 s
-[Task 5/25] Current/Best: 12.19/ 23.26 GFLOPS | Progress: (20/20) | 10.93 s Done.
+[Task 5/25] Current/Best: 9.57/ 10.31 GFLOPS | Progress: (4/20) | 2.56 s
+[Task 5/25] Current/Best: 11.82/ 12.69 GFLOPS | Progress: (8/20) | 4.63 s
+[Task 5/25] Current/Best: 11.92/ 18.08 GFLOPS | Progress: (12/20) | 7.65 s
+[Task 5/25] Current/Best: 11.79/ 22.88 GFLOPS | Progress: (16/20) | 9.06 s
+[Task 5/25] Current/Best: 12.16/ 22.88 GFLOPS | Progress: (20/20) | 10.94 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.25/ 21.01 GFLOPS | Progress: (4/20) | 4.08 s
-[Task 6/25] Current/Best: 19.28/ 21.01 GFLOPS | Progress: (8/20) | 5.83 s
-[Task 6/25] Current/Best: 13.48/ 21.01 GFLOPS | Progress: (12/20) | 7.77 s
-[Task 6/25] Current/Best: 20.28/ 21.01 GFLOPS | Progress: (16/20) | 9.99 s
-[Task 6/25] Current/Best: 3.76/ 21.01 GFLOPS | Progress: (20/20) | 12.48 s Done.
+[Task 6/25] Current/Best: 12.37/ 20.90 GFLOPS | Progress: (4/20) | 4.07 s
+[Task 6/25] Current/Best: 19.10/ 20.90 GFLOPS | Progress: (8/20) | 5.84 s
+[Task 6/25] Current/Best: 13.43/ 20.90 GFLOPS | Progress: (12/20) | 7.79 s
+[Task 6/25] Current/Best: 20.06/ 20.90 GFLOPS | Progress: (16/20) | 10.06 s
+[Task 6/25] Current/Best: 3.70/ 20.90 GFLOPS | Progress: (20/20) | 12.62 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.38/ 13.11 GFLOPS | Progress: (4/20) | 3.60 s
-[Task 7/25] Current/Best: 20.53/ 21.39 GFLOPS | Progress: (8/20) | 5.11 s
-[Task 7/25] Current/Best: 16.22/ 21.39 GFLOPS | Progress: (12/20) | 7.00 s
-[Task 7/25] Current/Best: 12.48/ 21.39 GFLOPS | Progress: (16/20) | 9.02 s
-[Task 7/25] Current/Best: 6.48/ 21.94 GFLOPS | Progress: (20/20) | 11.46 s Done.
+[Task 7/25] Current/Best: 11.22/ 12.88 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 7/25] Current/Best: 20.29/ 21.14 GFLOPS | Progress: (8/20) | 5.15 s
+[Task 7/25] Current/Best: 16.19/ 21.14 GFLOPS | Progress: (12/20) | 7.06 s
+[Task 7/25] Current/Best: 12.31/ 21.14 GFLOPS | Progress: (16/20) | 9.11 s
+[Task 7/25] Current/Best: 6.31/ 21.78 GFLOPS | Progress: (20/20) | 11.57 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.02/ 14.26 GFLOPS | Progress: (4/20) | 2.90 s
-[Task 8/25] Current/Best: 9.31/ 14.26 GFLOPS | Progress: (8/20) | 8.03 s
-[Task 8/25] Current/Best: 12.82/ 14.26 GFLOPS | Progress: (12/20) | 14.50 s
-[Task 8/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (16/20) | 16.58 s
-[Task 8/25] Current/Best: 19.79/ 19.79 GFLOPS | Progress: (20/20) | 23.66 s Done.
+[Task 8/25] Current/Best: 9.85/ 13.90 GFLOPS | Progress: (4/20) | 2.92 s
+[Task 8/25] Current/Best: 9.51/ 13.90 GFLOPS | Progress: (8/20) | 8.12 s
+[Task 8/25] Current/Best: 12.51/ 13.90 GFLOPS | Progress: (12/20) | 14.70 s
+[Task 8/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (16/20) | 16.83 s
+[Task 8/25] Current/Best: 20.14/ 20.14 GFLOPS | Progress: (20/20) | 23.99 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.56/ 16.02 GFLOPS | Progress: (4/20) | 11.91 s
-[Task 9/25] Current/Best: 23.76/ 23.76 GFLOPS | Progress: (8/20) | 13.67 s
-[Task 9/25] Current/Best: 8.41/ 23.76 GFLOPS | Progress: (12/20) | 16.19 s
-[Task 9/25] Current/Best: 17.99/ 23.76 GFLOPS | Progress: (16/20) | 19.04 s
-[Task 9/25] Current/Best: 9.36/ 23.76 GFLOPS | Progress: (20/20) | 27.50 s
+[Task 9/25] Current/Best: 14.31/ 15.82 GFLOPS | Progress: (4/20) | 11.95 s
+[Task 9/25] Current/Best: 23.40/ 23.40 GFLOPS | Progress: (8/20) | 13.74 s
+[Task 9/25] Current/Best: 8.28/ 23.40 GFLOPS | Progress: (12/20) | 16.33 s
+[Task 9/25] Current/Best: 17.86/ 23.40 GFLOPS | Progress: (16/20) | 19.23 s
+[Task 9/25] Current/Best: 9.06/ 23.40 GFLOPS | Progress: (20/20) | 27.88 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.49/ 18.49 GFLOPS | Progress: (4/20) | 2.54 s
-[Task 10/25] Current/Best: 15.76/ 18.49 GFLOPS | Progress: (8/20) | 4.16 s
-[Task 10/25] Current/Best: 12.84/ 19.05 GFLOPS | Progress: (12/20) | 5.69 s
-[Task 10/25] Current/Best: 19.13/ 20.62 GFLOPS | Progress: (16/20) | 6.78 s
-[Task 10/25] Current/Best: 8.99/ 20.62 GFLOPS | Progress: (20/20) | 8.29 s Done.
+[Task 10/25] Current/Best: 18.35/ 18.35 GFLOPS | Progress: (4/20) | 2.60 s
+[Task 10/25] Current/Best: 15.50/ 18.35 GFLOPS | Progress: (8/20) | 4.27 s
+[Task 10/25] Current/Best: 12.64/ 18.66 GFLOPS | Progress: (12/20) | 5.82 s
+[Task 10/25] Current/Best: 19.21/ 20.29 GFLOPS | Progress: (16/20) | 6.93 s
+[Task 10/25] Current/Best: 8.92/ 20.29 GFLOPS | Progress: (20/20) | 8.48 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.54/ 18.38 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 11/25] Current/Best: 17.25/ 18.38 GFLOPS | Progress: (8/20) | 6.10 s
-[Task 11/25] Current/Best: 18.30/ 18.38 GFLOPS | Progress: (12/20) | 8.17 s
-[Task 11/25] Current/Best: 13.59/ 21.57 GFLOPS | Progress: (16/20) | 11.09 s
-[Task 11/25] Current/Best: 19.74/ 21.90 GFLOPS | Progress: (20/20) | 13.15 s Done.
+[Task 11/25] Current/Best: 12.17/ 18.13 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 11/25] Current/Best: 16.97/ 18.13 GFLOPS | Progress: (8/20) | 6.17 s
+[Task 11/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (12/20) | 8.25 s
+[Task 11/25] Current/Best: 13.41/ 21.22 GFLOPS | Progress: (16/20) | 11.13 s
+[Task 11/25] Current/Best: 19.46/ 21.66 GFLOPS | Progress: (20/20) | 13.21 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.93/ 18.25 GFLOPS | Progress: (4/20) | 5.69 s
-[Task 12/25] Current/Best: 5.34/ 18.25 GFLOPS | Progress: (8/20) | 9.59 s
-[Task 12/25] Current/Best: 19.15/ 19.23 GFLOPS | Progress: (12/20) | 11.54 s
-[Task 12/25] Current/Best: 15.70/ 19.23 GFLOPS | Progress: (16/20) | 14.46 s
-[Task 12/25] Current/Best: 15.41/ 19.23 GFLOPS | Progress: (20/20) | 16.40 s Done.
+[Task 12/25] Current/Best: 7.84/ 18.07 GFLOPS | Progress: (4/20) | 5.69 s
+[Task 12/25] Current/Best: 5.20/ 18.07 GFLOPS | Progress: (8/20) | 9.67 s
+[Task 12/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (12/20) | 11.66 s
+[Task 12/25] Current/Best: 15.50/ 18.90 GFLOPS | Progress: (16/20) | 14.59 s
+[Task 12/25] Current/Best: 15.10/ 18.90 GFLOPS | Progress: (20/20) | 16.51 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.84/ 17.62 GFLOPS | Progress: (4/20) | 3.66 s
-[Task 13/25] Current/Best: 16.30/ 21.45 GFLOPS | Progress: (8/20) | 6.23 s
-[Task 13/25] Current/Best: 19.86/ 21.81 GFLOPS | Progress: (12/20) | 9.16 s
-[Task 13/25] Current/Best: 12.49/ 21.81 GFLOPS | Progress: (16/20) | 12.57 s
-[Task 13/25] Current/Best: 19.22/ 21.81 GFLOPS | Progress: (20/20) | 14.86 s Done.
+[Task 13/25] Current/Best: 8.69/ 17.36 GFLOPS | Progress: (4/20) | 3.76 s
+[Task 13/25] Current/Best: 15.69/ 20.98 GFLOPS | Progress: (8/20) | 6.37 s
+[Task 13/25] Current/Best: 19.59/ 21.83 GFLOPS | Progress: (12/20) | 9.42 s
+[Task 13/25] Current/Best: 12.24/ 21.83 GFLOPS | Progress: (16/20) | 12.88 s
+[Task 13/25] Current/Best: 18.70/ 21.83 GFLOPS | Progress: (20/20) | 15.24 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.75/ 13.75 GFLOPS | Progress: (4/20) | 3.28 s
-[Task 14/25] Current/Best: 6.20/ 13.75 GFLOPS | Progress: (8/20) | 5.40 s
-[Task 14/25] Current/Best: 20.68/ 20.68 GFLOPS | Progress: (12/20) | 8.04 s
-[Task 14/25] Current/Best: 17.37/ 20.68 GFLOPS | Progress: (16/20) | 9.65 s Done.
+[Task 14/25] Current/Best: 12.28/ 13.25 GFLOPS | Progress: (4/20) | 3.43 s
+[Task 14/25] Current/Best: 6.12/ 13.34 GFLOPS | Progress: (8/20) | 5.63 s
+[Task 14/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (12/20) | 8.35 s
+[Task 14/25] Current/Best: 16.75/ 20.32 GFLOPS | Progress: (16/20) | 10.01 s Done.
-[Task 14/25] Current/Best: 17.60/ 20.68 GFLOPS | Progress: (20/20) | 11.34 s
+[Task 14/25] Current/Best: 16.98/ 20.32 GFLOPS | Progress: (20/20) | 11.75 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.43/ 17.66 GFLOPS | Progress: (4/20) | 2.67 s
-[Task 15/25] Current/Best: 14.57/ 18.42 GFLOPS | Progress: (8/20) | 4.01 s
-[Task 15/25] Current/Best: 10.55/ 22.60 GFLOPS | Progress: (12/20) | 6.23 s
-[Task 15/25] Current/Best: 20.83/ 22.60 GFLOPS | Progress: (16/20) | 9.41 s
-[Task 15/25] Current/Best: 9.84/ 22.60 GFLOPS | Progress: (20/20) | 10.41 s
+[Task 15/25] Current/Best: 16.15/ 17.62 GFLOPS | Progress: (4/20) | 2.75 s
+[Task 15/25] Current/Best: 14.51/ 17.98 GFLOPS | Progress: (8/20) | 4.10 s
+[Task 15/25] Current/Best: 10.38/ 22.34 GFLOPS | Progress: (12/20) | 6.36 s
+[Task 15/25] Current/Best: 20.45/ 22.34 GFLOPS | Progress: (16/20) | 10.05 s
+[Task 15/25] Current/Best: 9.70/ 22.34 GFLOPS | Progress: (20/20) | 11.08 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 19.63/ 19.63 GFLOPS | Progress: (4/20) | 2.87 s
-[Task 16/25] Current/Best: 3.09/ 19.63 GFLOPS | Progress: (8/20) | 4.47 s
-[Task 16/25] Current/Best: 19.69/ 19.69 GFLOPS | Progress: (12/20) | 5.67 s
-[Task 16/25] Current/Best: 18.39/ 19.69 GFLOPS | Progress: (16/20) | 7.03 s
-[Task 16/25] Current/Best: 10.43/ 22.66 GFLOPS | Progress: (20/20) | 9.16 s Done.
+[Task 16/25] Current/Best: 20.88/ 20.88 GFLOPS | Progress: (4/20) | 2.96 s
+[Task 16/25] Current/Best: 3.04/ 20.88 GFLOPS | Progress: (8/20) | 4.57 s
+[Task 16/25] Current/Best: 19.81/ 20.88 GFLOPS | Progress: (12/20) | 5.77 s
+[Task 16/25] Current/Best: 18.17/ 20.88 GFLOPS | Progress: (16/20) | 7.13 s
+[Task 16/25] Current/Best: 10.01/ 22.44 GFLOPS | Progress: (20/20) | 9.30 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.20/ 19.18 GFLOPS | Progress: (4/20) | 4.72 s
-[Task 17/25] Current/Best: 14.49/ 23.77 GFLOPS | Progress: (8/20) | 7.53 s
-[Task 17/25] Current/Best: 17.11/ 23.77 GFLOPS | Progress: (12/20) | 9.57 s
-[Task 17/25] Current/Best: 16.75/ 23.77 GFLOPS | Progress: (16/20) | 11.77 s
-[Task 17/25] Current/Best: 10.17/ 23.77 GFLOPS | Progress: (20/20) | 13.92 s Done.
+[Task 17/25] Current/Best: 13.27/ 18.76 GFLOPS | Progress: (4/20) | 4.83 s
+[Task 17/25] Current/Best: 14.36/ 23.28 GFLOPS | Progress: (8/20) | 7.73 s
+[Task 17/25] Current/Best: 17.05/ 23.28 GFLOPS | Progress: (12/20) | 9.79 s
+[Task 17/25] Current/Best: 16.52/ 23.28 GFLOPS | Progress: (16/20) | 12.06 s
+[Task 17/25] Current/Best: 10.05/ 23.28 GFLOPS | Progress: (20/20) | 14.22 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.28/ 17.87 GFLOPS | Progress: (4/20) | 3.75 s
-[Task 18/25] Current/Best: 10.75/ 19.16 GFLOPS | Progress: (8/20) | 7.45 s
-[Task 18/25] Current/Best: 19.46/ 19.46 GFLOPS | Progress: (12/20) | 9.38 s
-[Task 18/25] Current/Best: 10.14/ 19.46 GFLOPS | Progress: (16/20) | 13.25 s
-[Task 18/25] Current/Best: 20.95/ 20.95 GFLOPS | Progress: (20/20) | 14.73 s Done.
+[Task 18/25] Current/Best: 11.44/ 17.91 GFLOPS | Progress: (4/20) | 3.82 s
+[Task 18/25] Current/Best: 10.60/ 17.91 GFLOPS | Progress: (8/20) | 7.51 s
+[Task 18/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (12/20) | 9.45 s
+[Task 18/25] Current/Best: 10.00/ 19.24 GFLOPS | Progress: (16/20) | 13.36 s
+[Task 18/25] Current/Best: 20.57/ 20.57 GFLOPS | Progress: (20/20) | 14.87 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.20/ 20.76 GFLOPS | Progress: (4/20) | 5.99 s
-[Task 19/25] Current/Best: 2.63/ 20.76 GFLOPS | Progress: (8/20) | 9.32 s
-[Task 19/25] Current/Best: 20.23/ 21.95 GFLOPS | Progress: (12/20) | 12.25 s
-[Task 19/25] Current/Best: 14.66/ 22.06 GFLOPS | Progress: (16/20) | 15.22 s
-[Task 19/25] Current/Best: 2.73/ 23.82 GFLOPS | Progress: (20/20) | 18.01 s Done.
+[Task 19/25] Current/Best: 7.17/ 20.23 GFLOPS | Progress: (4/20) | 6.07 s
+[Task 19/25] Current/Best: 2.61/ 20.23 GFLOPS | Progress: (8/20) | 9.44 s
+[Task 19/25] Current/Best: 19.93/ 21.69 GFLOPS | Progress: (12/20) | 12.42 s
+[Task 19/25] Current/Best: 14.23/ 21.69 GFLOPS | Progress: (16/20) | 15.50 s
+[Task 19/25] Current/Best: 2.70/ 23.77 GFLOPS | Progress: (20/20) | 18.32 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.40/ 15.03 GFLOPS | Progress: (4/20) | 3.31 s Done.
+[Task 20/25] Current/Best: 8.76/ 14.91 GFLOPS | Progress: (4/20) | 3.35 s Done.
Done.
-[Task 20/25] Current/Best: 10.74/ 15.03 GFLOPS | Progress: (8/20) | 6.78 s
-[Task 20/25] Current/Best: 2.35/ 16.60 GFLOPS | Progress: (12/20) | 10.69 s
-[Task 20/25] Current/Best: 12.57/ 16.60 GFLOPS | Progress: (16/20) | 14.56 s
-[Task 20/25] Current/Best: 12.83/ 22.48 GFLOPS | Progress: (20/20) | 16.63 s
+[Task 20/25] Current/Best: 9.89/ 14.91 GFLOPS | Progress: (8/20) | 6.75 s
+[Task 20/25] Current/Best: 2.32/ 16.42 GFLOPS | Progress: (12/20) | 10.63 s
+[Task 20/25] Current/Best: 12.35/ 16.42 GFLOPS | Progress: (16/20) | 14.35 s
+[Task 20/25] Current/Best: 12.93/ 22.30 GFLOPS | Progress: (20/20) | 16.46 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.50/ 18.00 GFLOPS | Progress: (4/20) | 3.24 s
-[Task 21/25] Current/Best: 14.77/ 18.00 GFLOPS | Progress: (8/20) | 4.85 s
-[Task 21/25] Current/Best: 1.63/ 18.00 GFLOPS | Progress: (12/20) | 6.99 s
-[Task 21/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 10.50 s
-[Task 21/25] Current/Best: 4.47/ 18.28 GFLOPS | Progress: (20/20) | 17.85 s
+[Task 21/25] Current/Best: 6.40/ 17.73 GFLOPS | Progress: (4/20) | 3.28 s
+[Task 21/25] Current/Best: 14.62/ 17.73 GFLOPS | Progress: (8/20) | 4.89 s
+[Task 21/25] Current/Best: 1.61/ 17.73 GFLOPS | Progress: (12/20) | 7.04 s
+[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (16/20) | 10.57 s
+[Task 21/25] Current/Best: 4.48/ 18.05 GFLOPS | Progress: (20/20) | 17.87 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.04 GFLOPS | Progress: (4/20) | 2.67 s
-[Task 22/25] Current/Best: 8.63/ 22.00 GFLOPS | Progress: (8/20) | 4.73 s
-[Task 22/25] Current/Best: 20.06/ 22.00 GFLOPS | Progress: (12/20) | 7.09 s
-[Task 22/25] Current/Best: 15.36/ 22.00 GFLOPS | Progress: (16/20) | 9.21 s
-[Task 22/25] Current/Best: 13.98/ 22.00 GFLOPS | Progress: (20/20) | 10.87 s Done.
+[Task 22/25] Current/Best: 8.62/ 22.30 GFLOPS | Progress: (8/20) | 4.71 s
+[Task 22/25] Current/Best: 20.34/ 22.30 GFLOPS | Progress: (12/20) | 7.11 s
+[Task 22/25] Current/Best: 15.56/ 22.30 GFLOPS | Progress: (16/20) | 9.21 s
+[Task 22/25] Current/Best: 14.30/ 22.30 GFLOPS | Progress: (20/20) | 10.93 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.53/ 20.90 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 23/25] Current/Best: 14.00/ 20.90 GFLOPS | Progress: (8/20) | 6.65 s
-[Task 23/25] Current/Best: 20.98/ 21.86 GFLOPS | Progress: (12/20) | 8.51 s
-[Task 23/25] Current/Best: 6.39/ 21.86 GFLOPS | Progress: (16/20) | 15.67 s
-[Task 23/25] Current/Best: 7.89/ 21.86 GFLOPS | Progress: (20/20) | 19.90 s Done.
+[Task 23/25] Current/Best: 17.82/ 21.13 GFLOPS | Progress: (4/20) | 3.20 s
+[Task 23/25] Current/Best: 14.25/ 21.13 GFLOPS | Progress: (8/20) | 6.57 s
+[Task 23/25] Current/Best: 21.22/ 22.12 GFLOPS | Progress: (12/20) | 8.40 s
+[Task 23/25] Current/Best: 6.52/ 22.12 GFLOPS | Progress: (16/20) | 15.48 s
+[Task 23/25] Current/Best: 7.81/ 22.12 GFLOPS | Progress: (20/20) | 19.66 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.40/ 8.40 GFLOPS | Progress: (4/20) | 11.79 s
-[Task 24/25] Current/Best: 3.79/ 8.40 GFLOPS | Progress: (8/20) | 23.02 s
-[Task 24/25] Current/Best: 4.32/ 8.40 GFLOPS | Progress: (12/20) | 33.78 s Done.
+[Task 24/25] Current/Best: 8.29/ 8.29 GFLOPS | Progress: (4/20) | 11.78 s
+[Task 24/25] Current/Best: 3.57/ 8.29 GFLOPS | Progress: (8/20) | 23.00 s
+[Task 24/25] Current/Best: 4.38/ 8.29 GFLOPS | Progress: (12/20) | 33.71 s Done.
Done.
-[Task 24/25] Current/Best: 6.13/ 8.69 GFLOPS | Progress: (16/20) | 39.61 s
-[Task 24/25] Current/Best: 3.43/ 8.83 GFLOPS | Progress: (20/20) | 45.53 s Done.
+[Task 24/25] Current/Best: 5.35/ 8.62 GFLOPS | Progress: (16/20) | 39.46 s
+[Task 24/25] Current/Best: 3.39/ 8.62 GFLOPS | Progress: (20/20) | 45.43 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.74 GFLOPS | Progress: (4/20) | 11.59 s
-[Task 25/25] Current/Best: 5.83/ 8.39 GFLOPS | Progress: (8/20) | 22.85 s
-[Task 25/25] Current/Best: 5.92/ 8.39 GFLOPS | Progress: (12/20) | 34.30 s
-[Task 25/25] Current/Best: 5.80/ 8.94 GFLOPS | Progress: (16/20) | 36.01 s
-[Task 25/25] Current/Best: 2.86/ 9.28 GFLOPS | Progress: (20/20) | 46.72 s
+[Task 25/25] Current/Best: 1.55/ 2.79 GFLOPS | Progress: (4/20) | 11.59 s
+[Task 25/25] Current/Best: 5.67/ 8.01 GFLOPS | Progress: (8/20) | 22.83 s
+[Task 25/25] Current/Best: 5.92/ 8.01 GFLOPS | Progress: (12/20) | 34.34 s
+[Task 25/25] Current/Best: 5.80/ 8.17 GFLOPS | Progress: (16/20) | 36.08 s
+[Task 25/25] Current/Best: 2.83/ 9.32 GFLOPS | Progress: (20/20) | 46.75 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -975,8 +975,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 402.03871841002183, 'median': 401.3822361000166, 'std': 1.676412929443544}
-unoptimized: {'mean': 483.53905445000237, 'median': 483.29701210000167, 'std': 0.7661273699735721}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 410.19464660001177, 'median': 409.9865518500337, 'std': 1.479414808980326}
+unoptimized: {'mean': 493.9443639300134, 'median': 494.06449910002266, 'std': 1.6148426721759408}
</pre></div>
</div>
</div>
@@ -990,7 +990,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 17.447 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 25.169 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index a0944d740..1d7b60228 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -521,7 +521,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.22e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.284e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 7d70d921c..d1aa8c1de 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -478,7 +478,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x221e1cf0)), stage(b, placeholder(b, 0x20838b20)), 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, 0x13e630d0)), stage(b, placeholder(b, 0xd1d8140)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 72a46b2f6..92f6212b6 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:21.588</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:17.160</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,46 +331,46 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:17.447</p></td>
+<td><p>10:25.169</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:10.812</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
+<td><p>01:01.661</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>00:58.514</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
+<td><p>00:53.974</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:29.292</p></td>
+<td><p>00:30.451</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:24.207</p></td>
+<td><p>00:24.524</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.679</p></td>
+<td><p>00:00.710</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.494</p></td>
+<td><p>00:00.512</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.137</p></td>
+<td><p>00:00.152</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><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></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_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></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 32ee29876..a3719b170 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -536,8 +536,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000006
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000009
+naive: 0.000008
</pre></div>
</div>
</div>
@@ -588,7 +588,7 @@ compile and run this new schedule with the parallel operation applied:</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallel: 0.000007
+parallel: 0.000006
</pre></div>
</div>
</div>
@@ -662,10 +662,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.355549998668722e-06 1.0
- naive 6.4793e-06 0.7754486540122838
-parallel 6.7145e-06 0.8035976089030419
- vector 2.45522e-05 2.9384301457009854
+ numpy 8.705270001883036e-06 1.0
+ naive 7.9467e-06 0.9128608300812093
+parallel 6.057599999999999e-06 0.695854350145335
+ vector 2.4561400000000002e-05 2.821440345295106
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -981,7 +981,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017542
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018048
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1024,7 +1024,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.254218
+none: 3.460671
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1091,7 +1091,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.299780
+blocking: 0.304582
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1152,7 +1152,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.333285
+vectorization: 0.341599
@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], []),
@@ -1209,7 +1209,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.112729
+loop permutation: 0.125728
@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], []),
@@ -1287,7 +1287,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.108889
+array packing: 0.109040
@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], []),
@@ -1363,7 +1363,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.108695
+block caching: 0.110982
@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], []),
@@ -1432,7 +1432,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.142479
+parallelization: 0.145363
@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], []),
@@ -1494,13 +1494,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.2542179431999996 1.0
- blocking 0.2997799901 0.09212044040455834
- vectorization 0.3332848599 0.10241626889078854
-loop permutation 0.1127285375 0.03464074609248501
- array packing 0.10888870320000002 0.03346078999642092
- block caching 0.1086951143 0.03340130138705948
- parallelization 0.1424787447 0.043782791191881595
+ none 3.4606707964999996 1.0
+ blocking 0.3045817251 0.0880123372058513
+ vectorization 0.3415989042 0.09870887012583834
+loop permutation 0.12572795650000002 0.036330516218750664
+ array packing 0.1090397093 0.03150825828630649
+ block caching 0.11098193730000001 0.03206948705211811
+ parallelization 0.1453633983 0.042004399391879575
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1532,6 +1532,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.661 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>