Skip to content

【Paddle Tensor 规范化第二期】elementwise_pow support complex #72518

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.

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

Merged
merged 9 commits into from
May 12, 2025

Conversation

fangfangssj
Copy link
Contributor

@fangfangssj fangfangssj commented Apr 27, 2025

PR Category

User Experience

PR Types

New features

Description

Pcard-75624
为elementwise_pow支持复数类型,
将pow_grad中GPU的实现由std切换到cuda,执行速度有提升
下面是随机生成不同shape的数据,执行100次反向的平均时间

shape std(ms) cuda(ms)
[10,10] 0.1047 0.1033
[100,100] 0.1044 0.1038
[1000,1000] 0.1877 0.1868
[10000,10000] 14.7237 14.6152
[20000,20000] 58.0524 58.0428

测试平台 nvidia p40,更大的tensor显存不够了,下面是测试代码
test.py.zip

Copy link

paddle-bot bot commented Apr 27, 2025

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.

@fangfangssj fangfangssj marked this pull request as draft May 7, 2025 12:27
@fangfangssj fangfangssj marked this pull request as ready for review May 7, 2025 12:27
Copy link
Contributor

@HydrogenSulfate HydrogenSulfate left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@fangfangssj
Copy link
Contributor Author

fangfangssj commented May 8, 2025

/re-run inference

@HydrogenSulfate HydrogenSulfate merged commit dd177ff into PaddlePaddle:develop May 12, 2025
72 of 77 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants