Matrix-Vector Multiplication Performances in Multi-Accelerator Architectures
Mathematical Problems of Computer Science · 01.06.2026 · 65 · 63-71
DOI: 10.51408/1963-0146 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Problems of Computer Science, online erschienen am 01.06.2026. Verfasst von Edita Gichunts.
Abstract (Originalsprache)
This paper presents the performance of symmetric and Hermitian matrix-vector multiplication on two Volta 100 graphics processors in single and double precision. The implementations were performed using the Magma library. The goal of this work is to present the implementations and performance evaluations of symmetric and Hermitian matrix-vector multiplication on 2 GPUs, and to compare their performance with that of a 1-GPU implementation.
Zitieren
APA
Gichunts, E. (2026). Matrix-Vector Multiplication Performances in Multi-Accelerator Architectures. Mathematical Problems of Computer Science, 65, 63-71. https://doi.org/10.51408/1963-0146
Vancouver
Gichunts E. Matrix-Vector Multiplication Performances in Multi-Accelerator Architectures. Mathematical Problems of Computer Science. 2026;65:63-71. doi:10.51408/1963-0146
BibTeX
@article{Gichunts2026,
author = {Gichunts, Edita},
title = {Matrix-Vector Multiplication Performances in Multi-Accelerator Architectures},
journal = {Mathematical Problems of Computer Science},
year = {2026},
volume = {65},
pages = {63--71},
doi = {10.51408/1963-0146}
}
EUVIMED