Matrix-matrix multiplication on heterogeneous platforms

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 : In this paper, we address the issue of implementing matrix-matrix multiplication on heterogeneous platforms. We target two different classes of heterogeneous computing resources: heterogeneous networks of workstations, and collections of heterogeneous clusters. Intuitively, the problem is to load balance the work with different-speed resources while minimizing the communication volume. We formally state this problem and prove its NP-completeness. Next we introduce a (polynomial) column-based heuristic, which turns out to be very satisfactory: we derive a theoretical performance guarantee for the heuristic, and we assess its practical usefulness through MPI experiments
Complete list of metadatas

https://hal.inria.fr/hal-00856648
Contributor : Equipe Roma <>
Submitted on : Monday, September 2, 2013 - 10:22:01 AM
Last modification on : Friday, November 23, 2018 - 1:40:03 PM

Links full text

Identifiers

Collections

Citation

Olivier Beaumont, Vincent Boudet, Fabrice Rastello, Yves Robert. Matrix-matrix multiplication on heterogeneous platforms. 2000 International Conference on Parallel Processing (ICPP'2000), 2000, Toronto, Canada. pp.289-298, ⟨10.1109/ICPP.2000.876144⟩. ⟨hal-00856648⟩

Share

Metrics

Record views

136