Dense Linear Algebra Kernels on Heterogeneous Platforms: Redistribution Issues

Olivier Beaumont 1 Arnaud Legrand 1 Fabrice Rastello 1 Yves Robert 1
1 REMAP - Regularity and massive parallel computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : Redistribution algorithms for dense linear algebra kernels on heterogeneous platforms are considered. In this context, processor speeds may well vary during the execution of a large kernel, which requires efficient strategies for redistributing the data along the computations. The proposed strategy is to redistribute data after some well-identified static phases and therefore is neither fully static nor fully dynamic. An optimal algorithm (under some assumptions) for redistributing data when computing the product of two matrices is presented.
Type de document :
Article dans une revue
Parallel Computing, Elsevier, 2002, 28, pp.155―185. 〈10.1016/S0167-8191(01)00134-X〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00789434
Contributeur : Arnaud Legrand <>
Soumis le : lundi 18 février 2013 - 11:51:05
Dernière modification le : mardi 5 mars 2013 - 16:02:36

Identifiants

Collections

Citation

Olivier Beaumont, Arnaud Legrand, Fabrice Rastello, Yves Robert. Dense Linear Algebra Kernels on Heterogeneous Platforms: Redistribution Issues. Parallel Computing, Elsevier, 2002, 28, pp.155―185. 〈10.1016/S0167-8191(01)00134-X〉. 〈hal-00789434〉

Partager

Métriques

Consultations de la notice

134