Add initial optional stream-k libraries #1347
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
AlexBrownAMD
requested review from
babakpst,
neoblizz,
bethune-bryant,
mahmoodw and
daineAMD
AlexBrownAMD
requested review from
jichangjichang,
KKyang,
aazz44ss,
vin-huang,
imcarsonliao,
hcman2,
Serge45,
Jinp800125,
TonyYHsieh and
solaslin
as code owners
yoichiyoshida
approved these changes
Nov 19, 2024
KKyang
approved these changes
Nov 20, 2024
jichangjichang
requested changes
Nov 20, 2024
|
Please provide the library size diff and building time diff. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adding initial stream-k libraries that can be toggled on by setting the environment variable: TENSILE_SOLUTION_SELECTION_METHOD=2
These libraries include Bgemm BBS and BSS, Hgemm HHS and HSS, and Sgemm for gfx942, gfx942_80cu, and gfx942_228cu.
All libraries have passed rocBLAS validation testing, and links to performance analysis are available in chat.