Conference
Open access
Aug 2026
High-Performance GEMV on AMD Zen 3 via Architecture-Specific AVX2/FMA Optimization
The General Matrix-Vector Multiply (GEMV) is a fundamental Level-2 BLAS operation appearing throughout scientific computing and numerical linear algebra. GEMV is inherently memory-bound, making effective cache use the dominant optimization factor.We present a hand-optimized GEMV kernel for AMD Zen 3, implemented using...
Rafał Lenart, B. Bylina, J. Bylina
· Conference on Computer Scien... · 0 citations