Skip to content
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

[GPU] Enable e8m0 JIT gemm scaling #2888

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[GPU] Enable e8m0 JIT gemm scaling #2888

wants to merge 2 commits into from

Conversation

kealan-barbieri
Copy link
Contributor

Description

Initial enabling of e8m0 scales in JIT gemm, baseline for mxfp enabling.

Checklist

General

  • Do all unit and benchdnn tests (make test and make test_benchdnn_*) pass locally for each commit?
  • Have you formatted the code using clang-format?

@github-actions github-actions bot added the platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel label Mar 14, 2025
@kealan-barbieri kealan-barbieri force-pushed the kealanba/f4_e3m0_jit_dst branch 2 times, most recently from cd6f71a to 8730a4d Compare March 17, 2025 16:21
@kealan-barbieri kealan-barbieri requested review from a team as code owners March 17, 2025 16:21
@kealan-barbieri kealan-barbieri force-pushed the kealanba/f4_e3m0_jit_dst branch 2 times, most recently from 2b9cc42 to 3b28704 Compare March 17, 2025 17:50
Base automatically changed from kealanba/f4_e3m0_jit_dst to main March 19, 2025 16:10
dzarukin
dzarukin approved these changes Mar 19, 2025
View reviewed changes
@kealan-barbieri kealan-barbieri force-pushed the kealanba/e8m0_gemm_scale branch from 3c5908a to 58b98e0 Compare March 19, 2025 21:54
@kealan-barbieri kealan-barbieri force-pushed the kealanba/e8m0_gemm_scale branch from 58b98e0 to 8155bf1 Compare March 19, 2025 21:56
@kealan-barbieri
Copy link
Contributor Author

make test
disable device_cpu
disable benchdnn_all
enable benchdnn_matmul

@kealan-barbieri kealan-barbieri force-pushed the kealanba/e8m0_gemm_scale branch from 8155bf1 to 73fd0d6 Compare March 20, 2025 21:13
@kealan-barbieri
Copy link
Contributor Author

make test
disable device_cpu
disable benchdnn_all
enable benchdnn_matmul

@kealan-barbieri kealan-barbieri force-pushed the kealanba/e8m0_gemm_scale branch from 73fd0d6 to d2540a1 Compare March 21, 2025 00:10
@kealan-barbieri
Copy link
Contributor Author

make test
disable device_cpu
disable benchdnn_all
enable benchdnn_matmul

@kealan-barbieri kealan-barbieri force-pushed the kealanba/e8m0_gemm_scale branch from d2540a1 to 8155bf1 Compare March 21, 2025 18:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@dzarukin dzarukin dzarukin approved these changes

@petercad petercad petercad approved these changes

Assignees
No one assigned
Labels
platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@kealan-barbieri @dzarukin @petercad