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

Matrix-multiplication units (MXUs) are now prevalent in every computingplatform. The key attribute that makes MXUs so successful is the semiringstructure, which allows tiling for both parallelism and data reuse.Nonetheless, matrix-multiplication is not the only algorithm with suchattributes. We find that many algorithms share the same structure and differ inonly the core operation; for example, using add-minimum instead ofmultiply-add. Algorithms with a semiring-like structure therefore havepotential to be accelerated by a general-purpose matrix operation architecture,instead of common MXUs.  In this paper, we propose SIMD$^2$, a new programming paradigm to supportgeneralized matrix operations with a semiring-like structure. SIMD$^2$instructions accelerate eight more types of matrix operations, in addition tomatrix multiplications. Since SIMD$^2$ instructions resemble amatrix-multiplication instruction, we are able to build SIMD$^2$ architectureon top of any MXU architecture with minimal modifications. We developed aframework that emulates and validates SIMD$^2$ using NVIDIA GPUs with TensorCores. Across 8 applications, SIMD2 provides up to 38.59$\times$ speedup andmore than 10.63$\times$ on average over optimized CUDA programs, with only 5%of full-chip area overhead.

SIMD$^2$: A Generalized Matrix Instruction Set for Accelerating Tensor Computation beyond GEMM