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
Complete list of metadatas

https://hal.inria.fr/hal-00856649
Contributor : Equipe Roma <>
Submitted on : Monday, September 2, 2013 - 10:22:02 AM
Last modification on : Friday, November 23, 2018 - 1:40:03 PM

Identifiers

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. pp.783-792, ⟨10.1109/IPDPS.2000.846065⟩. ⟨hal-00856649⟩

Share

Metrics

Record views

162