sycl: route small f32 matmuls to oneMKL, bypass oneDNN

[aicss-genai]

Overview

Authors

• @unrahul
• @ctao456
• @malsbat
• @YuningQiu
• @vvravi1
• @zhiqitao-intel

For f32 × f32 GEMMs where M*N*K < 256^3, go directly to oneapi::mkl::blas::column_major::gemm instead of the oneDNN wrapper. oneDNN primitive creation overhead dominates for small GEMMs on Intel Arc; bypassing it measurably improves token generation on small batch sizes.

Behavior unchanged when GGML_SYCL_DISABLE_DNN=1 (MKL path was already used) or when the GEMM is large (oneDNN still used). Threshold is a single constant and can be tuned or made configurable if needed.

Additional information

Part of work originally submitted as #22066 — splitting per reviewer request.

Requirements

• I have read and agree with the contributing guidelines
• AI usage disclosure: Yes. This work was partially produced with an agentic engineering approach: agents surface issues and explore experiments while engineers identify and reject candidates using domain knowledge. Human feedback involved.

[ggml-gh-bot]

Hi @aicss-genai, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

• Multiple open PRs from a new contributor: We limit new contributors (those without a previously merged PR) to 1 open PR at a time. You currently have 5 open PRs.

• AI-generated content: This project does not accept PRs, descriptions or commit messages that are fully or predominantly AI-generated. If you have used AI to assist you in writing code, please make sure to disclose that explicitly.

---

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.