Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Optimize performance of depthwise_conv_bwd #46362

Merged
merged 4 commits into from
Sep 30, 2022
Merged

Optimize performance of depthwise_conv_bwd #46362

merged 4 commits into from
Sep 30, 2022

Conversation

ZzSean
Copy link
Contributor

@ZzSean ZzSean commented Sep 21, 2022 •
edited
Loading

PR types

Performance optimization

PR changes

OPs

Describe

Optimize performance of depthwise_conv_bwd for input

  • Method:
  1. Reduce modulo calculations and other redundant calculations
  2. Modify the config of block/grid
  • Result:
config pytorch paddle dev paddle this PR speedup
input[2048, 1024, 4, 4]
filter[1024, 1, 4, 4]
stride=1
pad=0
dilation=1		 1.1070ms 2.9660ms 1.0798ms 2.75x

@paddle-bot
Copy link

paddle-bot bot commented Sep 21, 2022

你的PR提交成功，感谢你对开源项目的贡献!
请关注后续CI自动化测试结果，详情请参考Paddle-CI手册。
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

@ZzSean ZzSean merged commit f17a73e into PaddlePaddle:develop Sep 30, 2022
@ZzSean ZzSean mentioned this pull request Oct 11, 2022
Merged
@ZzSean ZzSean deleted the opt_dwconv_bwd branch November 7, 2022 03:01
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@LielinJiang LielinJiang LielinJiang approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@ZzSean @LielinJiang