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: [email protected] With regards, Apache Git Services
