-
Notifications
You must be signed in to change notification settings - Fork 5.6k
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
optimize elementwise_max_grad using new interfaces #37906
Conversation
Update forked PaddlePaddle
Update my fork
update from PaddlePaddle
Update forked paddle repo
Update USERNAME/paddle
update Paddle USERNAME repo
update username repo
update local paddlepaddle
update paddlepaddle
Thanks for your contribution! |
opbenchmark配置全吗? |
op-benchmark 配置是全的,6号、7号和8号是fp16,脚本不支持。此现象非此PR引入,原本就存在,需要处理,但不在此PR内。 |
Sorry to inform you that 2badce0's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM,但是当前已知问题是op benchmark中的case0和case1与dev分支有8~9%的下降,属于理论开销,在当前优化手段下无法避免
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM for PR-CI-OP-benchmark
PR types
Function optimization
PR changes
OPs
Describe
功能
该PR使用新的接口优化了elementwise_max的反向计算
效果
整体上讲,优化后性能均优于竞品;但就前4个配置,优化后较优化前性能差;其他配置优化后性能显著优于优化前:
整体上,优化3(适配多输出代码优化后)较优化1(reduce接口优化)、优化2(三元functor优化)均有显著提升;但当前前两个配置差于dev 10%左右;