Two-dimensional Block Partitionings for the Parallel Sparse Cholesky Factorization : the Fan-in Method - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1997

Two-dimensional Block Partitionings for the Parallel Sparse Cholesky Factorization : the Fan-in Method

Abstract

This paper presents a discussion on 2D block mappings for the sparse Cholesky factorization on parallel MIMD architectures with distributed memory. It introduces the fan-in algorithm in a general manner and proposes several mapping strategies. The grid mapping with row balancing, inspired from Rothberg's work proved to be more robust than the original fan-out algorithm. Even more efficient is the proportional mapping, as show the experiments on a 32 processors IBM SP1 and on a Cray T3D. Subforest-to-subcube mappings are also considered and give good results on the T3D.
Fichier principal
Vignette du fichier
RR-3156.pdf (340.88 Ko) Télécharger le fichier

Dates and versions

inria-00073533 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00073533 , version 1

Cite

Bogdan Dumitrescu, Mathias Doreille, Jean-Louis Roch, Denis Trystram. Two-dimensional Block Partitionings for the Parallel Sparse Cholesky Factorization : the Fan-in Method. [Research Report] RR-3156, INRIA. 1997. ⟨inria-00073533⟩
137 View
138 Download

Share

Gmail Facebook Twitter LinkedIn More