Abstract
One of the objectives of the EUREKA project PARSIM is to develop a distributed memory version of the COSI oil reservoir simulation package. As with most application packages, it is essential that the parallel version of COSI remains as faithful as possible to the original sequential code — the top level of the code must be hardware independent so users can run the same code on different hardware configurations and obtain more or less identical results.
This goal imposes some severe constraints on a key part of the simulator package — the linear equation solver. Parallel versions of both a sparse direct and a sparse iterative solver are required to maintain compatibility. In the following we provide an overview of how we have attempted to provide an integrated support environment for both solvers, what decisions have been made on the basic iterative technique and on the preconditioning to use and how these decisions were made.
This work was funded by the U.K.'s Department of Trade and Industry and by the Danish Erhvervsfremmestyrelsen as part of the EUREKA Project EU 638, PARSIM.
Preview
Unable to display preview. Download preview PDF.
References
K. Aziz and A. Settari, Petroleum Reservoir Simulation, Applied Science Publ., London, England, 1979.
N. Houbak, SESYS — A sparse matrix linear equation solver: Users Guide, Rapport nr. 12, Ris/o/ National Laboratory, Technical University of Denmark, June, 1985.
J. Larsen and T. Christensen, A parallel sparse matrix solver, Nordic Transputer Applications, IOS Press 1991.
C. Addison, B. Beattie, N. Brown, R. Cook, B. Stevens, and D. Watson. Distributed objects: sequential objects with parallel performance. In Proc. Sixth SIAM Conf. Parallel Processing for Sci. Comput., 1993.
R. Barrett, M. Berry, T. Chan, J. Demmel, J. Donato, J. Dongarra, V. Eijkhout, R. Pozo, C. Romine and H. van der Vorst, Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, SIAM, Philadelphia, 1993.
I. S. Duff, R. G. Grimes, and J. G. Lewis. Sparse matrix test problems. ACM Trans. Math. Software, 15:1–14, 1989.
R. W. Freund. A transpose-free quasi-minimal residual algorithm for non-Hermitian linear systems. SIAM J. Sci. Statist. Comput., 14:470–482, 1993.
R. W. Freund, G. H. Golub, and N. M. Nachtigal. Recent advances in Lanczos-based iterative methods for non-symmetric linear systems. Tech. Rept., RIACS, NASA Ames Research Center, Moffat Field, CA, 1992.
M. Seager, A SLAP for the Masses, Lawrence Livermore Nat. Laboratory Technical Report UCRL-100267, December, 1988.
T. A. Davis. User's guide for the unsymmetric-pattern multifrontal package (UMF-PACK). Tech. Rept. TR-93-020, Comput. and Information Sci. Dept., Univ. Florida, Gainsville, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Addison, C., Christensen, T., Larsen, J., Oliver, T., Sunderland, A. (1994). Supporting an oil reservoir simulator in a distributed memory environment. In: Gentzsch, W., Harms, U. (eds) High-Performance Computing and Networking. HPCN-Europe 1994. Lecture Notes in Computer Science, vol 796. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020396
Download citation
DOI: https://doi.org/10.1007/BFb0020396
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57980-9
Online ISBN: 978-3-540-48406-6
eBook Packages: Springer Book Archive