Abstract
Solving large nonsymmetric sparse linear systems on distributed memory multiprocessors is an active research area. We present a loop-level parallelized generic LU algorithm which comprises analysefactorize and solve stages. To further exploit matrix sparsity and parallelism, the analyse step looks for a set of compatible pivots. Sparse techniques are applied until the reduced submatrix reaches a threshold density. At this point, a switch to dense routines takes place in both analyse-factorize and solve stages. The SPMD code follows a sparse cyclic distribution to map the system matrix onto a P× Q processor mesh. Experimental results show a good behavior of our sequential algorithm compared with a standard generic solver: the MA48 routine. Additionally, a parallel version on the Cray T3E exhibits high performance in terms of speed-up and efficiency.
The work described in this paper was supported by the Ministry of Education and Science (CI-CYT) of Spain under project TIC96-1125-C03, by the European Union under contract BRITE-EURAM III BE95-1564, by the Human Capital and Mobility programme of the European Union under project ERB4050P1921660, and by the Training and Research on Advanced Computing Systems (TRACS) at the Edinburgh Parallel Computing Centre (EPCC)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. Alaghband. Parallel sparse matrix solution and performance. Parallel Computing, 21(9):1407–1430, 1995.
R. Asenjo and E.L. Zapata. Parallel pivots lu algorithm on the Cray T3E. Technical Report UMA-DAC-99/01, Dept. of Computer Architecture, University of Mlaga, Spain, http://www.ac.uma.es/, 1998.
E. Chu and A. George. Gaussian elimination with partial pivoting and load balancing on a multiprocessor. Parallel Comput., 5:65–74, 1987.
T. A. Davis. A parallel algorithm for sparse unsymmetric LU factorization. PhD thesis, Center for Supercomputing Research and Development, Univ. of Illinois, Urbana, IL, September 1989.
T. A. Davis and P. C. Yew. A nondeterministic parallel algorithm for general unsymmetric sparse LU factorization. SIAM J. Matrix Anal. Appl., 11:383–402, 1990.
Tim Davis. Sparse matrix collection. At URL http://www.cise.ufl.edu/ davis/.
J.J. Dongarra, I.S. Duff, D.C. Sorensen, and H.A. van der Vorst. Solving Linear Systems on Vector and Shared Memory Computers. Society for Industrial and Applied Mathematics, 1991.
I.S. Duff, A.M. Erisman, and J.K. Reid. Direct Methods for Sparse Matrices. Oxford University Press, Oxford, U.K., 1986.
I.S. Duff, R.G. Grimes, and J.G. Lewis. User’s guide for the Harwell-Boeing sparse matrix collection (Release I). Technical report, CERFACS, Toulouse, France, 1992.
I.S. Duff and J.K. Reid. The design of MA48: A code for the direct solution of sparse unsymmetric linear systems of equations. ACM Trans. Math. Softw., 22(2):187–226, June 1996.
C. Fu, X. Jiao, and T. Yang. Effcient sparse lu factorization with partial pivoting on distributed memory architectures. IEEE Transaction on Parallel and Distributed Systems, 9(2):109–125, February 1998.
K. Gallivan, B. Marsolf, and H.A.G. Wijshoff. Solving large nonsymmetric sparse linear systems using MCSPARSE. Parallel Computing, 22(10):1291–1333, 1996.
G. A. Geist and C. H. Romine. LU factorization algorithm on distributed-memory multiprocessor architecture. SIAM J. Sci. Statist. Comput., 9:639–649, 1989.
A. Gupta, G. Karypis, and V. Kumar. Highly scalable parallel algorithms for sparse matrix factorization. IEEE Transactions on Parallel and Distributed Systems, 8(5), 1995. Available at URL: http://www.cs.umn.edu/~kumar.
J. Koster and R.H. Bisseling. An improved algorithm for parallel sparse LU decomposition on a distributed memory multiprocessor. In J.G. Lewis, editor, Fifth SIAM Conference on Applied Linear Algebra, pages 397–401, 1994.
X. Li. Sparse Gaussian Elimination on High Performance Computers. PhD thesis, CS, UC Berkeley, 1996.
A. F. van der Stappen, R. H. Bisseling, and J. G. G. van de Vorst. Parallel sparse LU decomposition on a mesh network of transputers. SIAM J. Matrix Anal. Appl., 14(3):853–879, July 1993.
A.C.N. van Duin, P.C. Hansen, T. Ostromsky, H.A.G. Wijshoff, and Z. Zlatev. Improving the numerical stability and the performance of a parallel sparse solver. Computers Math. Applic., 30:81–96, 1995.
Z. Zlatev, J. Wa_sniewski, P.C. Hansen, and T. Ostromsky. PARASPAR: a package for the solution of large linear algebraic equations on parallel computers with shared memory. Technical Report 95-10, Tech. Univ. Denmark, Lyngby, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Asenjo, R., Zapata, E.L. (1999). Parallel Pivots LU Algorithm on the Cray T3E. In: Zinterhof, P., Vajteršic, M., Uhl, A. (eds) Parallel Computation. ACPC 1999. Lecture Notes in Computer Science, vol 1557. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49164-3_4
Download citation
DOI: https://doi.org/10.1007/3-540-49164-3_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65641-8
Online ISBN: 978-3-540-49164-4
eBook Packages: Springer Book Archive