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

src: cpu: aarch64: Re-enable matmul and convolution static quantisation through ACL. #2308

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

Conversation

renato-arantes
Copy link
Contributor

@renato-arantes renato-arantes commented Dec 22, 2024

Description

This is to re-enable matmul and conv static quantization operations through ACL. Currently, the supported data type combinations are s8:s8:s8 and u8:s8:u8. Neoverse-N1 is skipped until failing tests are fixed.

Previous PR: #2198

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?

@renato-arantes renato-arantes requested review from a team as code owners December 22, 2024 17:57
@renato-arantes renato-arantes force-pushed the static_quant2 branch 2 times, most recently from 88cf5e0 to 5cec04d Compare December 22, 2024 20:47
@renato-arantes
Copy link
Contributor Author

Hi @mgouicem, it's the same as before but more restrictive with Neoverse-N1 until the failing tests are fixed.

src/cpu/aarch64/acl_gemm_convolution.cpp Outdated Show resolved Hide resolved
@github-actions github-actions bot added the platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 label Dec 23, 2024
@theComputeKid theComputeKid added this to the v3.7 milestone Jan 8, 2025
@Radu2k
Copy link
Contributor

Radu2k commented Jan 8, 2025

@mgouicem @dzarukin Could we have someone review this please?

src/common/convolution_pd.hpp Outdated Show resolved Hide resolved
src/common/convolution_pd.hpp Outdated Show resolved Hide resolved
src/cpu/aarch64/acl_convolution_utils.hpp Outdated Show resolved Hide resolved
src/cpu/aarch64/acl_convolution_utils.hpp Show resolved Hide resolved
src/cpu/aarch64/acl_gemm_convolution.cpp Outdated Show resolved Hide resolved
src/cpu/aarch64/matmul/acl_lowp_matmul_sq.cpp Outdated Show resolved Hide resolved
src/cpu/aarch64/matmul/acl_lowp_matmul_sq.hpp Show resolved Hide resolved
src/cpu/aarch64/matmul/acl_lowp_matmul_sq.hpp Outdated Show resolved Hide resolved
src/cpu/aarch64/matmul/acl_lowp_matmul_sq.hpp Outdated Show resolved Hide resolved
src/cpu/cpu_convolution_list.cpp Outdated Show resolved Hide resolved
@mgouicem
Copy link
Contributor

mgouicem commented Jan 9, 2025

Hi @renato-arantes I see that you added a merge commit, please rebase your branch instead as we try to keep a linear history.

@renato-arantes renato-arantes force-pushed the static_quant2 branch 2 times, most recently from 3443f78 to e0cc129 Compare January 9, 2025 12:07
@vpirogov
Copy link
Member

vpirogov commented Jan 9, 2025

@renato-arantes, please resolve conflicts.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
Projects
None yet
Development

Successfully merging this pull request may close these issues.

7 participants