Abstract
We present analytical performance models for the numerical factorization phase of the multifrontal method for sparse matrices. Using a concise characterization of parallel architectures, we provide upper-bound estimates for the speedups observed on actual test problems taken from scientific and engineering applications. Representative architectures include an iPSC/2, iPSC/860, various clusters of workstations, and supercomputers connected by HIPPI interfaces. Simulation results suggest that the effective parallelism of these problems is quite sensitive to the communication bandwidth of the underlying architecture and load imbalances in the computational graph due to irregular data patterns.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
P. R. Amestoy, MUPS: Subroutine Library Specification, CERFACS, June 1991.
J. J. Dongarra, I. S. Duff, D. C. Sorensen, H. A. van der Host, Solving Linear Systems on Vector and Shared Memory Computers, SIAM, 1991.
I. S. Duff, “Parallel implementation of multifrontal schemes,” Parallel Computing, North-Holland, Vol. 3, pp. 193–204, 1986.
I. S. Duff, R. G. Grimes, J. G. Lewis, “Sparse Matrix Problems,” ACM Trans. Math. Softw., Vol 14, pp. 1–14, 1989.
I. S. Duff, L. S. Johnson, “Node Orderings and Concurrency in Structurally-Symmetric Sparse Problems,” Parallel Supercomputing: Methods, Algorithms, and Applications, John Wiley & Sons Ltd., 1989.
I. S. Duff, J. K. Reid, “The Multifrontal Solution of Unsymmetric Sets of Linear Equations,” SIAM J. Sci. Stat. Comput., Vol. 5, No. 3, pp 633–641.
M. T. Heath, E. Ng, B. W. Peyton, “Parallel Algorithms for Sparse Linear Systems,” SIAM Review, Vol. 33, No. 3, pp 420–460, 1991.
R. Lucas, T. Blank, J. Tiemann, “A Parallel Solution Method for Large Sparse Systems of Equations,” IEEE Transactions on Computer-Aided Design, Vol. CAD-6, No. 6, November 1987, pp. 981–991.
L. S. Ostrouchov, M. T. Heath, C. H. Romine, “Modeling Speedup in Parallel Sparse Matrix Factorization,” Technical Report ORNL/TM-11786, Oak Ridge National Laboratory, Oak Ridge, TN, 1990.
R. Pozo, “Performance Modeling of Parallel Architectures for Scientific Computing”, Ph. D. Thesis, University of Colorado, Boulder, 1991.
Yang and A. Gerasoulis, “PYRROS: Static scheduling and code generation for message passing multiprocessors,” Proc. of 6th ACM Inter. Conf. on Supercomputing, Washington D.C., July, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pozo, R. (1992). Performance modeling of sparse matrix methods for distributed memory architectures. In: Bougé, L., Cosnard, M., Robert, Y., Trystram, D. (eds) Parallel Processing: CONPAR 92—VAPP V. VAPP CONPAR 1992 1992. Lecture Notes in Computer Science, vol 634. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55895-0_469
Download citation
DOI: https://doi.org/10.1007/3-540-55895-0_469
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55895-8
Online ISBN: 978-3-540-47306-0
eBook Packages: Springer Book Archive