Computer Science – Distributed – Parallel – and Cluster Computing
Scientific paper
2006-12-06
Computer Science
Distributed, Parallel, and Cluster Computing
Scientific paper
This paper is aimed at designing efficient parallel matrix-product algorithms for heterogeneous master-worker platforms. While matrix-product is well-understood for homogeneous 2D-arrays of processors (e.g., Cannon algorithm and ScaLAPACK outer product algorithm), there are three key hypotheses that render our work original and innovative: - Centralized data. We assume that all matrix files originate from, and must be returned to, the master. - Heterogeneous star-shaped platforms. We target fully heterogeneous platforms, where computational resources have different computing powers. - Limited memory. Because we investigate the parallelization of large problems, we cannot assume that full matrix panels can be stored in the worker memories and re-used for subsequent updates (as in ScaLAPACK). We have devised efficient algorithms for resource selection (deciding which workers to enroll) and communication ordering (both for input and result messages), and we report a set of numerical experiments on various platforms at Ecole Normale Superieure de Lyon and the University of Tennessee. However, we point out that in this first version of the report, experiments are limited to homogeneous platforms.
Dongarra Jack
Pineau Jean-Francois
Robert Yves
Shi Zhiao
Vivien Frédéric
No associations
LandOfFree
Revisiting Matrix Product on Master-Worker Platforms does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Revisiting Matrix Product on Master-Worker Platforms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Revisiting Matrix Product on Master-Worker Platforms will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-452146