A Preliminary Out-of-Core Extension of a Parallel Multifrontal Solver
GUERMOUCHE, Abdou
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Algorithms and high performance computing for grand challenge applications [SCALAPPLIX]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Algorithms and high performance computing for grand challenge applications [SCALAPPLIX]
GUERMOUCHE, Abdou
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Algorithms and high performance computing for grand challenge applications [SCALAPPLIX]
< Réduire
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Algorithms and high performance computing for grand challenge applications [SCALAPPLIX]
Langue
en
Communication dans un congrès
Ce document a été publié dans
Proceedings of Euro-Par 2006 Parallel Processing, Proceedings of Euro-Par 2006 Parallel Processing, Euro-Par 2006 Parallel Processing, 2006. 2006p. 1053-1063
Résumé en anglais
The memory usage of sparse direct solvers can be the bottleneck to solve large-scale problems. This paper describes a first implementation of an out-of-core extension to a parallel multifrontal solver (MUMPS). We show that ...Lire la suite >
The memory usage of sparse direct solvers can be the bottleneck to solve large-scale problems. This paper describes a first implementation of an out-of-core extension to a parallel multifrontal solver (MUMPS). We show that larger problems can be solved on limited-memory machines with reasonable performance, and we illustrate the behaviour of our parallel out-of-core factorization. Then we use simulations to discuss how our algorithms can be modified to solve much larger problems.< Réduire
Origine
Importé de halUnités de recherche