Parallel matrix multiplication on heterogeneous networks of workstations

Matrix multiplication is taken as a test bed for parallel processing on heterogeneous networks of workstations (local area networks) used as parallel machines. Two algorithms are proposed taking into account the specific kind of parallel hardware provided by local area networks, and experimentation...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Tinetti, Fernando Gustavo, Luque Fadón, Emilio
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2002
Materias:
Ciencias Informáticas
Parallel
Languages
Cluster Computing
Heterogenous Parallel Computers
High Performance Computing
Performance Evaluation
Linear Algebra Applications
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23051
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23051
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Parallel
Languages
Cluster Computing
Heterogenous Parallel Computers
High Performance Computing
Performance Evaluation
Linear Algebra Applications
spellingShingle Ciencias Informáticas
Parallel
Languages
Cluster Computing
Heterogenous Parallel Computers
High Performance Computing
Performance Evaluation
Linear Algebra Applications
Tinetti, Fernando Gustavo
Luque Fadón, Emilio
Parallel matrix multiplication on heterogeneous networks of workstations
topic_facet Ciencias Informáticas
Parallel
Languages
Cluster Computing
Heterogenous Parallel Computers
High Performance Computing
Performance Evaluation
Linear Algebra Applications
description Matrix multiplication is taken as a test bed for parallel processing on heterogeneous networks of workstations (local area networks) used as parallel machines. Two algorithms are proposed taking into account the specific kind of parallel hardware provided by local area networks, and experimentation is used to drive the evaluation and identification of possible performance loss. A specific broadcast communication between processes of a parallel application is also proposed, taking advantage of the Ethernet interconnection network to achieve optimized performance. A special emphasis is place on already installed networks of workstations, which provide a hardware zero cost parallel computer; but a homogeneous Beowulf-class system is used to show how the algorithms are also useful on current classical high performance parallel computing with clusters.
format Objeto de conferencia
Objeto de conferencia
author Tinetti, Fernando Gustavo
Luque Fadón, Emilio
author_facet Tinetti, Fernando Gustavo
Luque Fadón, Emilio
author_sort Tinetti, Fernando Gustavo
title Parallel matrix multiplication on heterogeneous networks of workstations
title_short Parallel matrix multiplication on heterogeneous networks of workstations
title_full Parallel matrix multiplication on heterogeneous networks of workstations
title_fullStr Parallel matrix multiplication on heterogeneous networks of workstations
title_full_unstemmed Parallel matrix multiplication on heterogeneous networks of workstations
title_sort parallel matrix multiplication on heterogeneous networks of workstations
publishDate 2002
url http://sedici.unlp.edu.ar/handle/10915/23051
work_keys_str_mv AT tinettifernandogustavo parallelmatrixmultiplicationonheterogeneousnetworksofworkstations
AT luquefadonemilio parallelmatrixmultiplicationonheterogeneousnetworksofworkstations
bdutipo_str Repositorios
_version_ 1764820468029718529

Ejemplares similares