DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
Rechercher
(titres de publication, de périodique et noms de colloque inclus)
2006-09-25 - Colloque/Article dans les actes avec comité de lecture - Anglais - 8 page(s)

Manneback Pierre , Dongmo Jiogo Clovis, Kuonen P., "Well balanced sparse matrix-vector multiplication on a parallel heterogeneous system" in IEEE International Conference on Cluster Computing, Barcelona, Spain, 2006

  • Codes CREF : Mathématiques (DI1100), Analyse numérique (DI1123), Analyse de systèmes informatiques (DI2572)
  • Unités de recherche UMONS : Informatique (F114)
Texte intégral :

Abstract(s) :

(Anglais) This paper discusses well balanced implementations of sparse matrix-vector multiplication on heterogeneous environments. A new heuristic is proposed for balancing the computing load over the processors proportionally to their power. This is done by defining a distribution model which splits the sparse matrix in k-way partitions, in order to minimize the total execution time. An implementation of the sparse matrix vector multiplication in heterogeneous environment using parallel object-oriented programming model POP-C++ shows that this ID-partitioning heuristic improve greatly the performance of the product, in comparison with block row decomposition