Parallel, multigrain iterative solvers for hiding network latencies on MPPs and networks of clusters

Parallel Computing

Volumn 29, Issue 9, 2003, Pages 1237-1259

  McCombs, James R ^a   Stathopoulos, Andreas ^a  

^a The College of William and Mary   (United States)

Author keywords

Block methods; Eigenvalues; Jacobi Davidson; Latency; Multigrain parallelism

Indexed keywords

EIGENVALUES AND EIGENFUNCTIONS; ITERATIVE METHODS; LINEAR SYSTEMS; NEURAL NETWORKS; PROBLEM SOLVING;

PARALLEL ITERATIVE SOLVERS;

PARALLEL PROCESSING SYSTEMS;

EID: 0141532037     PISSN: 01678191     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8191(03)00101-7     Document Type: Conference Paper

References (37)

1. Saad Y., Schultz M.H. GMRES: a generalized minimal residual algorithm for solving nonsymmetric linear systems. SIAM J. Sci. Stat. Comput. 7:1986;856-869.
2. Cullum J., Willoughby R.A. Lanczos algorithms for large symmetric eigenvalue computations. Theory of Progress in Scientific Computing; v. 3. vol. 1:1985;Birkhauser, Boston.
3. Saad Y. Iterative Methods for Sparse Linear Systems. 1996;PWS Publishing Company.
4. Parlett B.N. The Symmetric Eigenvalue Problem. 1998;SIAM, Philadelphia, PA.
5. Saad Y. A flexible inner-outer preconditioned GMRES algorithm. SIAM J. Sci. Comput. 14(2):1993;461-469.
6. Sleijpen G.L., van der Vorst H.A. A Jacobi-Davidson iteration method for linear eigenvalue problems. SIAM J. Matrix Anal. Appl. 17:1996;401-425.
7. O'Leary D.P. The block conjugate gradient algorithm and related methods. Linear Algebra Appl. 29:1980;293-322.
8. Golub G.H., Underwood R. The block Lanczos method for computing eigenvalues. Rice J.R. Mathematical Software III. 1977;361-377 Academic Press, New York.
9. Simoncini V., Gallopoulos E. A hybrid block gmres method for nonsymmetric systems with multiple right-hand sides. J. Comput. Appli. Math. 66:1996;457-469.
10. Dongarra J.J., Duff I.S., Sorensen D.C., van der Vorst H. Numerical Linear Algebra for High Performance Computers. 1998;SIAM, Philadelphia, PA.
11. Hwang K., Xu Z. Scalable Parallel Computing. 1998;WCB/McGraw-Hill.
12. Foster I., Kesselman C. The Grid - Blueprint for a New Computing Infrastructure. 1998;Morgan Kaufmann.
13. Hennessy J.L., Patterson D.A. Computer Architecture A Quantitative Approach. second ed. 1996;Morgan Kaufmann, San Francisco, CA.
14. Chronopoulos A. s-step iterative methods for (non)symmetric (in)definite linear systems. SIAM J. Numer. Anal. 28(6):1991;1776-1789.
15. de Sturler E., der Vorst H.V. Reducing the effect of global communication in GMRES(m) and CG on parallel distributed memory computers. Appl. Numer. Math. 18(4):1995;441-459.
16. Aykanat C., Ozgüner F., Scott D. Vectorization and parallelization of the conjugate gradient algorithm on hypercube-connected vector processors. Microprocess. Microprogram. 29:1990;67-82.
17. Stathopoulos A., Fischer C.F. Reducing synchronization on the parallel Davidson method for the large, sparse, eigenvalue problem. Supercomputing'93. 1993;172-180 IEEE Comput. Soc. Press, Los Alamitos, CA.
18. O'Leary D.P. Parallel implementation of the block conjugate gradient algorithm. Parallel Comput. 5:1987;127-139.
19. Bertsekas D.P., Tsitsiklis J.N. Parallel and Distributed Computation: Numerical Methods. 1989;Prentice Hall, Englewood Cliffs, NJ.
20. Stathopoulos A., McCombs J.R. A parallel, block, Jacobi-Davidson implementation for solving large eigenproblems on coarse-grain environments. 1999 International Conference on Parallel and Distributed Processing Techniques and Applications. 1999;2920-2926 CSREA Press.
21. McCombs J.R., Stathopoulos A. Multigrain parallelism for eigenvalue computations on networks of clusters. Proceedings of the Eleventh IEEE International Symposium on High Performance Distributed Computing. 2002;143-149 IEEE, Los Alamitos, CA.
22. Y. Saad, K. Wu, Parallel SPARSe matrix LIBrary (P_SPARSLIB): the iterative solvers module, Tech. Rep. 94-008, Army High Performance Computing Research Center, Minneapolis, 1994.
23. Karypis G., Kumar V. A parallel algorithm for multilevel graph partitioning and sparse matrix ordering. J. Parallel Distributed Comput. 48:1998;71-85.
24. J.R. McCombs, R.T. Mills, A. Stathopoulos, Dynamic load balancing of an iterative eigensolver on networks of heterogeneous clusters, in: Proceedings of the 17th International Parallel and Distributed Processing Symposium, 2003, on CDROM, ISBN 0-7695-1926-1.
25. Saad Y. Numerical Methods for Large Eigenvalue Problems. 1992;Manchester University Press.
26. M. Genseberger, G.L.G. Sleijpen, Alternative correction equations in the Jacobi-Davidson method, Tech. Rep. 1073, Department of Mathematics, University of Utrecht, 1999.
27. B. Liu, Numerical algorithms in chemistry: algebraic methods, Tech. Rep. LBL-8158, Lawrence Berkeley National Laboratory, 1978.
28. Bai Z., Demmel J., Dongarra J., Ruhe A., van der Vorst H. Templates for the Solution of Algebraic Eigenvalue Problems: A Practical Guide. 2000;SIAM, Philadelphia.
29. Sleijpen G.L.G., Booten A.G.L., Fokkema D.R., van der Vorst H.A. Jacobi-Davidson type methods for generalized eigenproblems and polynomial eigenproblems. BIT. 36(3):1996;595-633.
30. A. Farazdel, G. Archondo-Callao, et al., Understanding and using the SP Switch, Tech. Rep. SG24-5161-00, IBM Corporation, 1999.
31. RS/6000 SP: SP Switch and SP Switch2 performance, Tech. Rep., IBM Corporation, June 2001.
32. Bergamaschi L., Pini G., Sartoretto F. Parallel preconditioning of a sparse eigensolver. Parallel Comput. 27(7):2001;963-976.
33. T. Davis, University of Florida Sparse Matrix Collection, NA Digest 97 (23) (1997).
34. Y. Saad, SPARSKIT: a basic tool kit for sparse matrix computations, Tech. Rep., Computer Science Department, University of Minnesota, Minneapolis, MN, version 2, June 1994.
35. E. Chow, ParaSails: parallel sparse approximate inverse (least-squares) preconditioner, Tech. Rep., Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, 2001.
36. Fokkema D.R., Sleijpen G.L.G., van der Vorst H.A. Jacobi-Davidson style QR and QZ algorithms for the partial reduction of matrix pencils. SIAM J. Sci. Comput. 20(1):1998.
37. LAM/MPI Parallel Computing: LAM Version 6.5.2. Available from 〈http://www.lam-mpi.org/6.5/〉, May 2003.