Efficient hybrid parallelisation of tiled algorithms on SMP clusters

Drosinos, N; Koziris, N

dc.contributor.author	Drosinos, N	en
dc.contributor.author	Koziris, N	en
dc.date.accessioned	2014-03-01T01:58:37Z
dc.date.available	2014-03-01T01:58:37Z
dc.date.issued	2009	en
dc.identifier.issn	17427185	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/28694
dc.subject	Hybrid parallelisation	en
dc.subject	Load balancing	en
dc.subject	MPI	en
dc.subject	Nested loops	en
dc.subject	OpenMP	en
dc.subject	SMP clusters	en
dc.subject	Tiling transformation	en
dc.subject.other	Hybrid parallelisation	en
dc.subject.other	Load balancing	en
dc.subject.other	MPI	en
dc.subject.other	Nested loops	en
dc.subject.other	OpenMP	en
dc.subject.other	SMP clusters	en
dc.subject.other	Tiling transformation	en
dc.subject.other	Embedded systems	en
dc.subject.other	Message passing	en
dc.subject.other	Shape memory effect	en
dc.title	Efficient hybrid parallelisation of tiled algorithms on SMP clusters	en
heal.type	journalArticle	en
heal.identifier.primary	10.1504/IJCSE.2009.027003	en
heal.identifier.secondary	http://dx.doi.org/10.1504/IJCSE.2009.027003	en
heal.publicationDate	2009	en
heal.abstract	This paper emphasises on load balancing issues associated 0with hybrid parallelisation of tiled algorithms onto SMP clusters. The intrinsic load imbalance in hybrid parallelisation derives from the fact that message passing libraries often provide limited multi-threading support, thus allowing only the master thread to perform inter-node message passing communication. In order to mitigate this effect, we propose a generic method for the application of load balancing on the coarse-grain hybrid model for the appropriate load distribution among the working threads. We investigate both static and dynamic load balancing, and experimentally evaluate three balancing variations against kernel benchmarks. Copyright © 2009, Inderscience Publishers.	en
heal.journalName	International Journal of Computational Science and Engineering	en
dc.identifier.doi	10.1504/IJCSE.2009.027003	en
dc.identifier.volume	4	en
dc.identifier.issue	2	en
dc.identifier.spage	112	en
dc.identifier.epage	126	en