Accelerating vector calculations on GPU

Publikace:
Accelerating vector calculations on GPU

Článekopen accesspeer-reviewedpublished

dc.contributor.author	Grondžák, Karol
dc.contributor.author	Martincová, Penka
dc.contributor.author	Šuch, Ondřej
dc.date.accessioned	2011-12-14T08:43:27Z
dc.date.available	2011-12-14T08:43:27Z
dc.date.issued	2011
dc.description.abstract	Multicore computational accelerators such as Graphics Processor Units(GPUs) became common for gaining high-performance computing on a larger scale.Programming GPUs requires detailed knowledge of the underlying architecture in order to get maximum performance. In this paper we present solution of vector distance calculation on NVIDIA’s parallel computing architecture CUDA (Common Unified Device Architecture), where we optimize the performance of a parallel algorithm and get significant speedup.	cze
dc.format	p. 52-61	eng
dc.identifier.issn	1211-555X (Print)
dc.identifier.issn	1804-8048 (Online)
dc.identifier.uri	https://hdl.handle.net/10195/42168
dc.language.iso	eng
dc.peerreviewed	yes	eng
dc.publicationstatus	published	eng
dc.publisher	Univerzita Pardubice	cze
dc.relation.ispartof	Scientific papers of the University of Pardubice. Series D, Faculty of Economics and Administration. 19 (1/2011)	eng
dc.subject	vector calculations	eng
dc.subject	GPU	eng
dc.subject	CUDA	eng
dc.subject	parallel programming	eng
dc.title	Accelerating vector calculations on GPU	eng
dc.type	Article	cze
dspace.entity.type	Publication

Nyní se zobrazuje 1 - 1 z 1

Nyní se zobrazuje 1 - 1 z 1