English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

GEMM with the small size of input matrices is becoming widely used in manyfields like HPC and machine learning. Although many famous BLAS librariesalready supported small GEMM, they cannot achieve near-optimal performance.This is because the costs of pack operations are high and frequent boundaryprocessing cannot be neglected. This paper proposes an input-aware adaptivetuning framework(IAAT) for small GEMM to overcome the performance bottlenecksin state-of-the-art implementations. IAAT consists of two stages, theinstall-time stage and the run-time stage. In the run-time stage, IAAT tilesmatrices into blocks to alleviate boundary processing. This stage utilizes aninput-aware adaptive tile algorithm and plays the role of runtime tuning. Inthe install-time stage, IAAT auto-generates hundreds of kernels of differentsizes to remove pack operations. Finally, IAAT finishes the computation ofsmall GEMM by invoking different kernels, which corresponds to the size ofblocks. The experimental results show that IAAT gains better performance thanother BLAS libraries on ARMv8 platform.

IAAT: A Input-Aware Adaptive Tuning framework for Small GEMM