Abstract
In this paper, we present an analytical performance model of the parallel left-right looking out-of-core LU factorization algorithm. We show the accuracy of the performance prediction for a prototype implementation in the ScaLAPACK library. We will show that with a correct distribution of the matrix and with an overlapof IO by computation, we obtain performances similar to those of the in-core algorithm. To get such performances, the size of the physical main memory only need to be proportional to the product of the matrix order (not the matrix size) by the ratio of the IO bandwidth and the computation rate: There is no need of large main memory for the factorization of huge matrix!
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This work is supported by a grant of the “Pôle de Modélisation de la Région Picardie”.
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
L. S. Blackford, J. Choi, A. Cleary, E. D’Azevedo, J. Demmel, I. Dhillon, J. Dongarra, S. Hammarling, G. Henry, A. Petitet, K. Stanley, D. Walker, and R. C. Whaley. ScaLAPACK Users’ Guide. SIAM, Philadelphia, 1997.
Eddy Caron, Olivier Cozette, Dominique Lazure, and Gil Utard. Virtual Memory Management in Data Parallel Applications. In HPCN’99, High Performance Computing and Networking Europe, volume 1593 of LNCS. Springer, April 1999.
J. Choi, J. Demmel, I. Dhillon, J. Dongarra, S. Ostrouchov, A. Petitet, K. Stanley, D. Walker, and R. C. Whaley. LAPACK Working Note: ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers-Design Issues and Performances. Technical Report UT-CS-95, Department of Computer Science, University of Tennessee, 1995.
F. Desprez, S. Domas, and B. Tourancheau. Optimization of the ScaLAPACK LU factorization routine using Communication/Computation overlap. In Europar’96 Parallel Processing, volume 1124 of LNCS. Springer, August 1996.
Jack J. Dongarra, Sven Hammarling, and David W. Walker. Key Concepts for Parallel Out-Of-Core LU Factorization. Parallel Computing, 23, 1997.
Wesley C. Reiley and Robert A. van de Geijn. POOCLAPACK: Parallel Out-of-Core Linear Algebra Package. Technical report, Department of Computer Sciences, The University of Texas, Austin, October 1999.
J.M. Del Rosario and A. Choudhary. High performance I/O for massively parallel computers: Problems and Prospects. IEEE Computer, 27(3):59–68, 1994.
Sivan Toledo and Fred G. Gustavson. The design and implementation of SOLAR, a portable library for scalable out-of-core linear algebra computations. In Proceedings of the Fourth Workshop on Input/Output in Parallel and Distributed Systems, Philadelphia, May 1996. ACM Press.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Caron, E., Lazure, D., Utard, G. (2000). Performance Prediction and Analysis of Parallel Out-of-Core Matrix Factorization. In: Valero, M., Prasanna, V.K., Vajapeyam, S. (eds) High Performance Computing — HiPC 2000. HiPC 2000. Lecture Notes in Computer Science, vol 1970. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44467-X_15
Download citation
DOI: https://doi.org/10.1007/3-540-44467-X_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41429-2
Online ISBN: 978-3-540-44467-1
eBook Packages: Springer Book Archive