Selecting the tile shape to reduce the total communication volume

Drosinos, N; Goumas, G; Koziris, N

dc.contributor.author	Drosinos, N	en
dc.contributor.author	Goumas, G	en
dc.contributor.author	Koziris, N	en
dc.date.accessioned	2014-03-01T02:44:11Z
dc.date.available	2014-03-01T02:44:11Z
dc.date.issued	2006	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31738
dc.subject	Data Dependence	en
dc.subject	Distributed Memory Architecture	en
dc.subject	Transformation Group	en
dc.subject.other	Communication systems	en
dc.subject.other	Computer architecture	en
dc.subject.other	Distributed computer systems	en
dc.subject.other	Optimization	en
dc.subject.other	Partial differential equations	en
dc.subject.other	Cartesian process grids	en
dc.subject.other	Communication volume	en
dc.subject.other	Communication-aware tile shape	en
dc.subject.other	Parallel execution time	en
dc.subject.other	Parallel processing systems	en
dc.title	Selecting the tile shape to reduce the total communication volume	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IPDPS.2006.1639377	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IPDPS.2006.1639377	en
heal.identifier.secondary	1639377	en
heal.publicationDate	2006	en
heal.abstract	In this paper we revisit the tile-shape selection problem, that has been extensively discussed in bibliography. An efficient approach is proposed for the selection of a suitable tile shape, based on the minimization of the process communication volume. We consider the large family of applications that arise from the discretization of partial differential equations (PDEs). Practical experience has shown that for such applications and distributed memory architectures, minimizing the total communication volume is more important than minimizing the total number of parallel execution steps. We formulate a new method to determine an appropriate communication-aware tile shape, i.e. the one that reduces the communication volume for a fixed number of processes. Our approach is equivalent to defining a proper Cartesian process grid with MPI_Cart_Create, which means that it can be incorporated in applications in a straightforward manner. Our experimental results illustrate that by selecting the tile shape with the proposed method, the total parallel execution time is significantly reduced due to the minimization of the communication volume, despite the fact that a few more parallel execution steps are required. © 2006 IEEE.	en
heal.journalName	20th International Parallel and Distributed Processing Symposium, IPDPS 2006	en
dc.identifier.doi	10.1109/IPDPS.2006.1639377	en
dc.identifier.volume	2006	en