Parallel LU Factorization of Band Matrices on SMP Systems

In this paper we present two routines for the LU factorization of band matrices that target (parallel) SMP architectures and expose coarser-grain parallelism than their LAPACK counterpart. Preliminary experimental results on two different parallel platforms show some initial benefits for the new app...

Full description

Saved in:
Bibliographic Details
Published inHigh Performance Computing and Communications pp. 110 - 118
Main Authors REMON, Alfredo, QUINTANA-ORTI, Enrique S, QUINTANA-ORTI, Gregorio
Format Book Chapter Conference Proceeding
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2006
Springer
SeriesLecture Notes in Computer Science
Subjects
Applied sciences
Band matrix
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Exact sciences and technology
LAPACK
LU factorization
multithreaded BLAS
Software
Symmetric Multiprocessor (SMP)
Band matrix
Multiprocessor
High performance
LU factorization
Symmetric configuration
Parallelism
Distributed computing
Online AccessGet full text

Cover

More Information
Summary:In this paper we present two routines for the LU factorization of band matrices that target (parallel) SMP architectures and expose coarser-grain parallelism than their LAPACK counterpart. Preliminary experimental results on two different parallel platforms show some initial benefits for the new approach.
Bibliography:This research was supported by the CICYT project TIN2005-09037-C02-02 and FEDER, and project No. P1B-2004-6 of the Fundación Caixa-Castelló/Bancaixa and UJI.
ISBN:3540393684
9783540393689
ISSN:0302-9743
1611-3349
DOI:10.1007/11847366_12