Optimizing Sparse Matrix-Vector Multiplication using index and value compression

Kourtis, K; Goumas, G; Koziris, N

dc.contributor.author	Kourtis, K	en
dc.contributor.author	Goumas, G	en
dc.contributor.author	Koziris, N	en
dc.date.accessioned	2014-03-01T02:45:43Z
dc.date.available	2014-03-01T02:45:43Z
dc.date.issued	2008	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32341
dc.subject	Data compression	en
dc.subject	Memory bandwidth	en
dc.subject	Sparse matrix	en
dc.subject.other	Bandwidth	en
dc.subject.other	Bandwidth compression	en
dc.subject.other	Numerical methods	en
dc.subject.other	Online searching	en
dc.subject.other	Telecommunication systems	en
dc.subject.other	Vectors	en
dc.subject.other	Compression methods	en
dc.subject.other	Data volumes	en
dc.subject.other	Index compressions	en
dc.subject.other	Memory bandwidth	en
dc.subject.other	Numerical values	en
dc.subject.other	Research works	en
dc.subject.other	Sparse matrix	en
dc.subject.other	Speed-up	en
dc.subject.other	Data compression	en
dc.title	Optimizing Sparse Matrix-Vector Multiplication using index and value compression	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1366230.1366244	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1366230.1366244	en
heal.publicationDate	2008	en
heal.abstract	Previous research work has identified memory bandwidth as the main bottleneck of the ubiquitous Sparse Matrix-Vector Multiplication kernel. To attack this problem, we aim at reducing the overall data volume of the algorithm. Typical sparse matrix representation schemes store only the nonzero elements of the matrix and employ additional indexing information to properly iterate over these elements. In this paper we propose two distinct compression methods targeting index and numerical values respectively. We perform a set of experiments on a large real-world matrix set and demonstrate that the index compression method can be applied successfully to a wide range of matrices. Moreover, the value compression method is able to achieve impressive speedups in a more limited yet important class of sparse matrices that contain a small number of distinct values. Copyright 2008 ACM.	en
heal.journalName	Conference on Computing Frontiers - Proceedings of the 2008 Conference on Computing Frontiers, CF'08	en
dc.identifier.doi	10.1145/1366230.1366244	en
dc.identifier.spage	87	en
dc.identifier.epage	96	en