Skip to content

feat(HSA ENV): tune ROCm runtime with HSA_NO_SCRATCH_RECLAIM and HSA_ENABLE_SDMA #32

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
Apr 22, 2025
Merged

feat(HSA ENV): tune ROCm runtime with HSA_NO_SCRATCH_RECLAIM and HSA_ENABLE_SDMA #32

merged 1 commit into from
Apr 22, 2025

Conversation

@Xiaoming-AMD
Copy link
Collaborator

@Xiaoming-AMD Xiaoming-AMD commented Apr 22, 2025

  • Set HSA_NO_SCRATCH_RECLAIM=1 to disable scratch memory reclaim, reducing allocation overhead and improving kernel launch performance.
  • Set HSA_ENABLE_SDMA=1 to enable SDMA engines for efficient memory transfers between host and device without blocking compute resources.
  • These settings help improve stability and performance for training and inference workloads on AMD GPUs.

wenxie-amd
wenxie-amd approved these changes Apr 22, 2025
View reviewed changes
Copy link
Contributor

@wenxie-amd wenxie-amd left a comment

Choose a reason for hiding this comment

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

LGTM

@wenxie-amd wenxie-amd merged commit 4e7c52b into main Apr 22, 2025
2 checks passed
@Xiaoming-AMD Xiaoming-AMD deleted the dev/xiaoming/env_optimize branch April 23, 2025 00:35
@Xiaoming-AMD Xiaoming-AMD changed the title [Feat] tune ROCm runtime with HSA_NO_SCRATCH_RECLAIM and HSA_ENABLE_SDMA feature(HSA ENV): tune ROCm runtime with HSA_NO_SCRATCH_RECLAIM and HSA_ENABLE_SDMA Jun 4, 2025
@Xiaoming-AMD Xiaoming-AMD changed the title feature(HSA ENV): tune ROCm runtime with HSA_NO_SCRATCH_RECLAIM and HSA_ENABLE_SDMA feat(HSA ENV): tune ROCm runtime with HSA_NO_SCRATCH_RECLAIM and HSA_ENABLE_SDMA Jun 25, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@wenxie-amd wenxie-amd wenxie-amd 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

@Xiaoming-AMD @wenxie-amd