Logo des Repositoriums
 
Konferenzbeitrag

Improving GPU Matrix Multiplication by Leveraging Bit Level Granularity and Compression

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2023

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Quelle

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

In this paper we introduce BEAM as a novel approach to perform GPU based matrix multiplication on compressed elements. BEAM allows flexible handling of bit sizes for both input and output elements. First evaluations show promising speedups compared to an uncompressed state-of-the-art matrix multiplication algorithm provided by nvidia.

Beschreibung

Fett, Johannes; Schwarz, Christian; Kober, Urs; Habich, Dirk; Lehner, Wolfgang (2023): Improving GPU Matrix Multiplication by Leveraging Bit Level Granularity and Compression. BTW 2023. DOI: 10.18420/BTW2023-49. Bonn: Gesellschaft für Informatik e.V.. ISBN: 978-3-88579-725-8. pp. 763-772. Dresden, Germany. 06.-10. März 2023

Zitierform

Tags