Abstract
In this paper, we describe a parallel implementation for the reduction of general and symmetric matrices to Hessenberg and tridiagonal form, respectively. The methods are based on LAPACK sequential codes and use a panel-wrapped mapping of matrices to nodes. Results from experiments on the Intel Touchstone Delta are given.
Original language | English |
---|---|
Pages (from-to) | 973-982 |
Number of pages | 10 |
Journal | Parallel Computing |
Volume | 18 |
Issue number | 9 |
DOIs | |
State | Published - Sep 1992 |
Funding
While parallel implementations of algorithms for solving linear systems have been widely studied \[4, 9\], the reduction to condensed form has not enjoyed the same attention. A parallel * This work was supported in part by the National Science Foundation Science and TechnologyC enter Cooperative Agreement No. CCR-8809615, by the Applied Mathematical Science Research Program, Office of Energy Research, US Department of Energy, under Contract DE-AC05-84OR21400, and by the Army Research Oftice under DARPA Contract DAAL 03-91-c-0046. Most of this work was performed while the second author was on leave at the University of Tennessee. Correspondence to: Jack J. Dongarra, Dept. of Computer Sciences, Univ. of Tennessee, Knoxville," IN 37996, USA.
Keywords
- Eigenvalue problem
- LAPACK
- distributed memory architecture
- linear algebra