Dynamic load balancing within a parallel iterative linear system solver
We present a parallel iterative linear system solver package which is designed to run efficiently on heterogeneous and dynamically changing platforms (like workstation clusters) by applying heterogeneous data distribution and dynamic load balancing.
Unable to display preview. Download preview PDF.
- 1.Peter Christen. PAISS — a parallel iterative linear system solver package with dynamic load balancing. Technical report, Institut für Informatik, Universität Basel, 1998. To be published.Google Scholar
- 2.Scott A. Hutchinson, John N. Shadid, and Ray S. Tuminaro. Aztec User's Guide, Version 1.1. Massively Parallel Computing Research Laboratory, Sandia National Laboratories, Albuquerque, October 1995.Google Scholar
- 3.Brian K. Schmidt and Vaidy S. Sunderam. Empirical analysis of overheads in cluster environments. Concurrency: Practice and Experience, 6(1):1–32, February 1994.Google Scholar