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.

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

[GPU] Fp8 compute backports #2266

Open
wants to merge 10 commits into
base: main
Choose a base branch
from
Open

Conversation

kealan-barbieri
Copy link
Contributor

@kealan-barbieri kealan-barbieri commented Dec 13, 2024

Description

Backport of mixed fp8 support, additional scale support for compute primitivies.

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?

@kealan-barbieri kealan-barbieri added platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel backport labels Dec 13, 2024
@kealan-barbieri kealan-barbieri requested review from a team as code owners December 13, 2024 17:46
@github-actions github-actions bot removed the backport label Dec 13, 2024
src/common/convolution.cpp Outdated Show resolved Hide resolved
src/common/convolution.cpp Show resolved Hide resolved
src/common/matmul.cpp Outdated Show resolved Hide resolved
src/common/matmul.cpp Outdated Show resolved Hide resolved
src/common/matmul_pd.hpp Outdated Show resolved Hide resolved
src/common/matmul_pd.hpp Outdated Show resolved Hide resolved
@@ -195,7 +207,13 @@ struct matmul_pd_t : public primitive_desc_t {
sc.group_dims_[0] == 1
&& K() % sc.group_dims_[1] == 0);
} else {
ok = ok && (mask == 0);
ok = ok
Copy link
Contributor

Choose a reason for hiding this comment

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

Here must be a check for fp8 versus classic quantization.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I dont think it is required. With these changes gemm supports dst scales whenever dst is an integer or fp8 so there should be no difference in treatment. Attempts to use dst scales with non-fp8 float dst will be filtered in attr checks.

tests/benchdnn/inputs/matmul/option_set_fp8_mixed Outdated Show resolved Hide resolved
tests/benchdnn/inputs/matmul/option_set_fp8_mixed Outdated Show resolved Hide resolved
tests/benchdnn/utils/cfg.hpp Outdated Show resolved Hide resolved
@kealan-barbieri kealan-barbieri force-pushed the kealanba/compute_backports branch 2 times, most recently from 8aa5c64 to accacad Compare December 18, 2024 23:09
@kealan-barbieri kealan-barbieri force-pushed the kealanba/compute_backports branch from accacad to 606af26 Compare December 19, 2024 00:03
@kealan-barbieri
Copy link
Contributor Author

make test
disable device_cpu
enable device_gpu
disable benchdnn_all
enable benchdnn_matmul
enable benchdnn_conv

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:tests platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants