Dynamic load balancing in parallel processing on non-homogeneous clusters

This paper analyzes the dynamic and static balancing of non-homogenous cluster architectures, simultaneously analyzing the theoretical parallel Speedup as well as the Speedup experimentally obtained. Three interconnected clusters have been used in which the machines within each cluster have homogene...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: De Giusti, Armando Eduardo, Naiouf, Marcelo, De Giusti, Laura Cristina, Chichizola, Franco
Formato: Articulo
Lenguaje:Inglés
Publicado: 2005
Materias:
Ciencias Informáticas
Parallel algorithms
cluster architectures
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/9604
http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Dec05-17.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-9604
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 algorithms
cluster architectures
spellingShingle Ciencias Informáticas
Parallel algorithms
cluster architectures
De Giusti, Armando Eduardo
Naiouf, Marcelo
De Giusti, Laura Cristina
Chichizola, Franco
Dynamic load balancing in parallel processing on non-homogeneous clusters
topic_facet Ciencias Informáticas
Parallel algorithms
cluster architectures
description This paper analyzes the dynamic and static balancing of non-homogenous cluster architectures, simultaneously analyzing the theoretical parallel Speedup as well as the Speedup experimentally obtained. Three interconnected clusters have been used in which the machines within each cluster have homogeneous processors although different among clusters. Thus, the set can be seen as a 25-processor heterogeneous cluster or as a multi-cluster scheme with subsets of homogeneous processors. A classical application (Parallel N-Queens) with a parallel solution algorithm, where processing predominates upon communication, has been chosen so as to go deep in the load balancing aspects (dynamic or static) without distortion of results caused by communication overhead. At the same time, three forms of load distribution in the processors (Direct Static, Predictive Static and Dynamic by Demand) have been studied, analyzing in each case parallel Speedup and load unbalancing regarding problem size and the processors used.
format Articulo
Articulo
author De Giusti, Armando Eduardo
Naiouf, Marcelo
De Giusti, Laura Cristina
Chichizola, Franco
author_facet De Giusti, Armando Eduardo
Naiouf, Marcelo
De Giusti, Laura Cristina
Chichizola, Franco
author_sort De Giusti, Armando Eduardo
title Dynamic load balancing in parallel processing on non-homogeneous clusters
title_short Dynamic load balancing in parallel processing on non-homogeneous clusters
title_full Dynamic load balancing in parallel processing on non-homogeneous clusters
title_fullStr Dynamic load balancing in parallel processing on non-homogeneous clusters
title_full_unstemmed Dynamic load balancing in parallel processing on non-homogeneous clusters
title_sort dynamic load balancing in parallel processing on non-homogeneous clusters
publishDate 2005
url http://sedici.unlp.edu.ar/handle/10915/9604
http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Dec05-17.pdf
work_keys_str_mv AT degiustiarmandoeduardo dynamicloadbalancinginparallelprocessingonnonhomogeneousclusters
AT naioufmarcelo dynamicloadbalancinginparallelprocessingonnonhomogeneousclusters
AT degiustilauracristina dynamicloadbalancinginparallelprocessingonnonhomogeneousclusters
AT chichizolafranco dynamicloadbalancinginparallelprocessingonnonhomogeneousclusters
bdutipo_str Repositorios
_version_ 1764820491603804161

Ejemplares similares