8000 Improving build time by removing the gfx11xx and host code from rccl_float8.h by mberenjk · Pull Request #1789 · ROCm/rccl · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Improving build time by removing the gfx11xx and host code from rccl_float8.h #1789

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 3 commits into from
Jul 9, 2025

Conversation

mberenjk
Copy link
Contributor
@mberenjk mberenjk commented Jul 2, 2025

Details

Do not mention proprietary info or link to internal work items in this PR.

Work item: "Internal", or link to GitHub issue (if applicable).
SWDEV-539929
What were the changes?
Removing the host side and gfx11 from OCP type check.

Why were the changes made?
The build time overhead is due to those specific architectures when the build includes all architectures (i.e., without -l).

How was the outcome achieved?
We achieved the build time reduction by excluding certain architectures from the build.

Additional Documentation:
What else should the reviewer know?

Approval Checklist

Do not approve until these items are satisfied.

  • Verify the CHANGELOG has been updated, if
    • there are any NCCL API version changes,
    • any changes impact library users, and/or
    • any changes impact any other ROCm library.

@mberenjk mberenjk changed the title Improving build time by removing the gfx11xx arch Improving build time by removing the gfx11xx and host code from rccl_float8.h Jul 2, 2025
@mberenjk mberenjk merged commit 697bee4 into ROCm:develop Jul 9, 2025
15 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.

3 participants
0