-
Notifications
You must be signed in to change notification settings - Fork 5.9k
【Hackathon 9th No.5】Add index check for index_sample gpu kernel #74848
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
【Hackathon 9th No.5】Add index check for index_sample gpu kernel #74848
Conversation
|
你的PR提交成功,感谢你对开源项目的贡献! |
bd5d73a to
1847aef
Compare
1847aef to
faaa7d0
Compare
|
/re-run all-failed |
请补充下paddleapitest回测的结果。#72637
|
done |
| PADDLE_ENFORCE(sample_idx >= 0 && sample_idx < input_length, | ||
| "Variable value (index) of OP(index_sample) " | ||
| "expected >= 0 and < %ld, but got %ld. Please check input " | ||
| "value.", | ||
| input_length, | ||
| sample_idx); |
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.
在cuda kernel中添加这些检查是十分不合理的,会影响cuda warp的执行效率,报错时也会产生特别多的重复日志。这部分检查需要想办法转化为在launch cuda kernel之前在CPU侧完成
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.
Done, 改成 copy 到 cpu 上进行检查了
|
/re-run all-failed |
|
close due to the following PR is merged: |

PR Category
Operator Mechanism
PR Types
Bug fixes
Description
Add index check for index_sample gpu kernel