Skip to Main content Skip to Navigation
Reports

Memory-based scheduling for a parallel multifrontal solver

Abdou Guermouche 1, 2 Jean-Yves l'Excellent 1, 2
1 REMAP - Regularity and massive parallel computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : The memory usage of sparse direct solvers can be the bottleneck to solve large-scale problems. This paper describes dynamic scheduling strategies that aim at reducing the memory usage of a parallel direct solver. Combined to static modifications of the tasks dependency graph, experiments show that such techniques have a good potential to improve the memory usage of a parallel multifrontal solver, MUMPS.
Document type :
Reports
Complete list of metadata

https://hal.inria.fr/inria-00071427
Contributor : Rapport de Recherche Inria <>
Submitted on : Tuesday, May 23, 2006 - 5:29:42 PM
Last modification on : Friday, June 25, 2021 - 3:40:05 PM

Identifiers

  • HAL Id : inria-00071427, version 1

Collections

Citation

Abdou Guermouche, Jean-Yves l'Excellent. Memory-based scheduling for a parallel multifrontal solver. [Research Report] RR-5162, LIP RR-2004-17, INRIA, LIP. 2004. ⟨inria-00071427⟩

Share

Metrics

Record views

383

Files downloads

720