You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/07/18 05:05:47 UTC
[GitHub] [incubator-mxnet] wuxun-zhang opened a new pull request #15584: Add
omp parallel optimization for _contrib_BilinearReisze2D
wuxun-zhang opened a new pull request #15584: Add omp parallel optimization for _contrib_BilinearReisze2D
URL: https://github.com/apache/incubator-mxnet/pull/15584
## Description ##
This PR aims to improve the performance of `_contrib_BilinearReisze2D` via omp parallel optimization.
This will be a great help to deploy Fully Convolutional Network model on CPU. @pengzhao-intel @ZhennanQin @TaoLv @zhanghang1989
The below table shows the speedup between w/ OMP and w/o OMP.
Before resize | After resize | w/o OMP (ms) | w/ OMP 28 cores (ms) | Speedup
-- | -- | -- | -- | --
shape: (1, 32, 32, 32) | shape: (1, 32, 480, 480) | 25.643921 | 5.877519 | **4.36**
shape: (2, 64, 32, 32) | shape: (2, 64, 480, 480) | 134.311175 | 32.115507 | **4.18**
shape: (1, 128, 64, 64) | shape: (1, 128, 480, 480) | 126.516438 | 34.05602 | **3.71**
shape: (32, 32, 32, 32) | shape: (32, 32, 480, 480) | 2262.586236 | 341.702771 | **6.62**
shape: (32, 32, 64, 64) | shape: (32, 32, 480, 480) | 2201.238561 | 339.254451 | **6.49**
## Checklist ##
### Essentials ###
- [x] Changes are complete (i.e. I finished coding on this PR)
- [x] All changes have test coverage:
- [x] To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services