Skip to content

[ROCM] fix bmm_kernel #45530

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
Merged
merged 1 commit into from
Aug 31, 2022
Merged

[ROCM] fix bmm_kernel #45530

merged 1 commit into from
Aug 31, 2022

Conversation

@ronny1996
Copy link
Contributor

@ronny1996 ronny1996 commented Aug 29, 2022 •
edited
Loading

PR types

Bug fixes

PR changes

Others

Describe

fix bmm_kernel

未知的bug，暂时解决

#44723 合入之后，BatchedGEMM 中调用 CUBlas::GEMM_STRIDED_BATCH / CUBlas::GEMM_STRIDED_BATCH 时，函数内的参数错位，CUBlas::GEMM_STRIDED_BATCH 正常

错位情况（倒数2个参数异常）：

rocblas_sgemm_strided_batched,N,N,16,16,512,1,0x7f98eda37000,16,8192,0x7f98eda27000,512,8192,0,0x7f98eda0c800,16,2199023255554,256,atomics_allowed

正常情况：

rocblas_sgemm_strided_batched,N,N,16,16,512,1,0x7f2b53e2e000,16,8192,0x7f2b53e09000,512,8192,0,0x7f2b53e3e000,16,256,2,atomics_allowed

qili93
qili93 approved these changes Aug 29, 2022
View reviewed changes
Copy link
Contributor

@qili93 qili93 left a comment

Choose a reason for hiding this comment

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

LGTM

ZzSean
ZzSean approved these changes Aug 31, 2022
View reviewed changes
Copy link
Contributor

@ZzSean ZzSean left a comment

Choose a reason for hiding this comment

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

LGTM for CI-OP-Benchmark

@ronny1996 ronny1996 merged commit 4478389 into PaddlePaddle:develop Aug 31, 2022
@ronny1996 ronny1996 deleted the fix_rocm branch August 31, 2022 02:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@qili93 qili93 qili93 approved these changes

@ZzSean ZzSean ZzSean 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.

3 participants

@ronny1996 @qili93 @ZzSean