Parallel algorithms for triangular sylvester equations: Design, scheduling and scalability issues
A new scalable algorithm for solving (quasi)triangular Sylvester equations on a logical 2D-toroidal processor grid is presented. Based on a performance model of the algorithm, a static scheduler chosing the optimal processor grid and block sizes for a rectangular block scatter (RBS) mapping of matrices is incorporated in the algorithm.
Scalability properties implying good scalability of the algorithm are also derived from the performance model. Performance results from our ScaLAPACK-like implementations on an 64 processor IBM SP verify the scalability potential of the algorithm.
Unable to display preview. Download preview PDF.
- 1.E. Anderson, Z. Bai, C. Bischof, J. Demmel, J. Dongarra, J. Du Croz, A. Greenbaum, A. Hammarling, A. McKenney, S. Ostrouchov, and D Sorensen. LAPACK Users Guide, Release 2.0. SIAM Press, September 1994.Google Scholar
- 5.J. Choi, J. J. Dongarra, R. Pozo, and D. W. Walker. ScaLAPACK: A Scalable Linear Algebra Library for Distributed Memory Concurrent Computers. Progress paper, Oak Ridge National Laboratory and University of Tennesee, 1991.Google Scholar
- 7.J. Dongarra and C. Whaley. A User’s Guide to the BLACS v1.0. LAPACK working note 94, Department of Computer Science, University of Tennessee, Knoxville, TN 37996, June 1995.Google Scholar
- 10.B. Kågström. A Direct Method for Reordering Eigenvalues in the Generalized Real Schur Form of a Regular Matrix Pair (A, B). In G. H. Golub M. S. Moonen and B.L.R. De Moor, editors, Linear Algebra for Large Scale and Real-Time Applications, pages 195–218. Kluwer Academic Publicher, 1993.Google Scholar
- 12.B. Kågström and P. Poromaa. Distributed Block Algorithms for the Triangular Sylvester Equation with Condition Estimator. In F. Andre’ and J.P. Verjus, editors, Hypercube and Distributed Computers, pages 233–248. North-Holland, 1989.Google Scholar
- 15.V. Kumar, A. Grama, and G. Karpys. Introduction to Parallel Computing. Benjamin/Cummings, September 1994.Google Scholar
- 16.R. Mathias. Condition Estimation for Matrix Functions via the Schur Decomposition. Technical report. Department of Matematics, College of William and Mary, Williamsburg, USA, October 1994.Google Scholar
- 17.P. Poromaa. Design Implementation and Performance for the Triangular Sylvester Equation with Condition Estimators. UMINF-189-90, Licentiate Thesis, Institute of Information Processing, Department of Computing Science, University of Umeå, Sweden, November 1990.Google Scholar
- 18.P. Poromaa. On Efficient and Robust Estimators for the Separation between two Regular Matrix Pairs with Applications in Condition Estimation. UMINF-95-05, Department of Computing Science, Umeå Uneversity, Sweden, August 1995.Google Scholar
- 19.P. Poromaa. High Performance Computing: Algorithms and Library Software for Sylvester Equations and Certain Eigenvalue Problems with Applications in Condition Estimators, PhD Thesis. UMINF-97.16, Department of Computing Science, University of Umeå, Sweden, May 1997.Google Scholar