Load balancing strategies for dense linear algebra kernels on heterogeneous two-dimensional grids

Olivier Beaumont 1 Vincent Boudet 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 : We study the implementation of dense linear algebra computations, such as matrix multiplication and linear system solvers, on two-dimensional (2D) grids of heterogeneous processors. For these operations, 2D-grids are the key to scalability and efficiency. The uniform block-cyclic data distribution scheme commonly used for homogeneous collections of processors limits the performance-of-these operations on heterogeneous grids to the speed of the slowest processor. We present and study more sophisticated data allocation strategies that balance the load on heterogeneous 2D-grids with respect to the performance of the processors. The usefulness of these strategies is demonstrated by simulation measurements for a heterogeneous network of workstations
Type de document :
Communication dans un congrès
14th International Parallel and Distributed Processing Symposium (IPDPS'2000), 2000, Cancun, Mexico. IEEE Computer Society Press, pp.783-792, 2000, 〈10.1109/IPDPS.2000.846065〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00856649
Contributeur : Equipe Roma <>
Soumis le : lundi 2 septembre 2013 - 10:22:02
Dernière modification le : mardi 16 janvier 2018 - 15:50:51

Identifiants

Collections

Citation

Olivier Beaumont, Vincent Boudet, Fabrice Rastello, Yves Robert. Load balancing strategies for dense linear algebra kernels on heterogeneous two-dimensional grids. 14th International Parallel and Distributed Processing Symposium (IPDPS'2000), 2000, Cancun, Mexico. IEEE Computer Society Press, pp.783-792, 2000, 〈10.1109/IPDPS.2000.846065〉. 〈hal-00856649〉

Partager

Métriques

Consultations de la notice

104