Change unroll for gfx94x

Open wenkaidu opened this issue 1 year ago • 3 comments

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).

What were the changes?
Change unroll for gfx94x

Why were the changes made?
Improve RCCL performance when GPU clock is lower under heavy workload

How was the outcome achieved?
Increase unroll factor

Additional Documentation:

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.

May 23 '24 14:05 wenkaidu

Is this draft no longer valid @wenkaidu ?

Jul 19 '24 20:07 corey-derochie-amd

this is used to track SWDEV-469533 which still open in mainline build

Jul 19 '24 20:07 wenkaidu

not intended for merge

Jul 19 '24 20:07 wenkaidu