Abstract
Sparse direct solvers, and in particular multifrontal methods, are widely used in various simulation problems. Because of their large memory requirements, the use of out-of-core solvers is compulsory for large-scale problems, where disks are used to extend the core memory. This study is at the junction of two previous independent works: it extends the problem of the minimization of the volume of I/O [4] in the multifrontal method to the more general flexible parent allocation algorithm [8]. We explain how to compute the I/O volume with respect to this scheme and propose an efficient greedy heuristic which significantly reduces the I/O volume on real-life problems in this new context.
Partially supported by ANR project SOLSTICE, ANR-06-CIS6-010.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
The BCSLIB Mathematical/Statistical Library, http://www.boeing.com/phantom/bcslib/
Agullo, E., Guermouche, A., L’Excellent, J.-Y.: Towards a parallel out-of-core multifrontal solver: Preliminary study. Research report 6120, INRIA. Also appeared as LIP report RR2007-06 (February 2007)
Agullo, E.: On the out-of-core factorization of large sparse matrices. Phd thesis, Ecole Normale Supérieure de Lyon (October 2008) (submitted)
Agullo, E., Guermouche, A., L’Excellent, J.-Y.: On reducing the I/O volume in a sparse out-of-core solver. In: Aluru, S., Parashar, M., Badrinath, R., Prasanna, V.K. (eds.) HiPC 2007. LNCS, vol. 4873, pp. 47–58. Springer, Heidelberg (2007)
Amestoy, P.R., Guermouche, A., L’Excellent, J.-Y., Pralet, S.: Hybrid scheduling for the parallel solution of linear systems. Parallel Computing 32(2), 136–156 (2006)
Amestoy, P.R., Puglisi, C.: An unsymmetrized multifrontal LU factorization. SIAM Journal on Matrix Analysis and Applications 24, 553–569 (2002)
Duff, I.S., Reid, J.K.: The multifrontal solution of indefinite sparse symmetric linear systems. ACM Transactions on Mathematical Software 9, 302–325 (1983)
Guermouche, A., L’Excellent, J.-Y.: Constructing memory-minimizing schedules for multifrontal methods. ACM Transactions on Mathematical Software 32(1), 17–32 (2006)
Karypis, G., Kumar, V.: MeTiS – A Software Package for Partitioning Unstructured Graphs, Partitioning Meshes, and Computing Fill-Reducing Orderings of Sparse Matrices – Version 4.0. University of Minnesota (September 1998)
Liu, J.W.H.: On the storage requirement in the out-of-core multifrontal method for sparse factorization. ACM Transactions on Mathematical Software 12, 127–148 (1986)
Liu, J.W.H.: The multifrontal method for sparse matrix solution: Theory and Practice. SIAM Review 34, 82–109 (1992)
Reid, J.K., Scott, J.A.: An out-of-core sparse Cholesky solver. Technical Report RAL-TR-2006-013, Rutherford Appleton Laboratory (2006) (Revised March 2007)
Rothberg, E., Schreiber, R.: Efficient methods for out-of-core sparse cholesky factorization. SIAM Journal on Scientific Computing 21(1), 129–144 (1999)
Rotkin, V., Toledo, S.: The design and implementation of a new out-of-Core sparse Cholesky factorization method. ACM Transactions on Mathematical Software 30(1), 19–46 (2004)
Schulze, J.: Towards a tighter coupling of bottom-up and top-down sparse matrix ordering methods. BIT 41(4), 800–841 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Agullo, E., Guermouche, A., L’Excellent, JY. (2008). On the I/O Volume in Out-of-Core Multifrontal Methods with a Flexible Allocation Scheme. In: Palma, J.M.L.M., Amestoy, P.R., Daydé, M., Mattoso, M., Lopes, J.C. (eds) High Performance Computing for Computational Science - VECPAR 2008. VECPAR 2008. Lecture Notes in Computer Science, vol 5336. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-92859-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-540-92859-1_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-92858-4
Online ISBN: 978-3-540-92859-1
eBook Packages: Computer ScienceComputer Science (R0)