H-Isoefficiency: Scalability Metric for Heterogeneous Systems

Scalability is one of the most important features in exascale computing. Most of this systems are heterogeneous and therefore it becomes necessary to develop models and metrics that take into account this heterogeneity. This paper presents a new expression of the isoefficiency function called H-isoe...

ver descrição completa

Detalhes bibliográficos
Autores: Bosque, Jose Luis, Robles, Oscar D., Toharia, Pablo, Pastor, Luis
Formato: artículo
Fecha de publicación:2010
País:España
Recursos:Universidad Rey Juan Carlos
Repositorio:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
OAI Identifier:oai:burjcdigital.urjc.es:10115/4691
Acesso em linha:http://hdl.handle.net/10115/4691
Access Level:acceso abierto
Palavra-chave:Informática
1203.02 Lenguajes Algorítmicos
id ES_183ad585e5bca096b2c8ef99dc73f890
oai_identifier_str oai:burjcdigital.urjc.es:10115/4691
network_acronym_str ES
network_name_str España
repository_id_str
spelling H-Isoefficiency: Scalability Metric for Heterogeneous SystemsBosque, Jose LuisRobles, Oscar D.Toharia, PabloPastor, LuisInformática1203.02 Lenguajes AlgorítmicosScalability is one of the most important features in exascale computing. Most of this systems are heterogeneous and therefore it becomes necessary to develop models and metrics that take into account this heterogeneity. This paper presents a new expression of the isoefficiency function called H-isoefficiency. This function can be applied for both homogeneous and heterogeneous systems and allows to analyze the scalability of a parallel system. Then, as an example, a theoretical a priori analysis of the scalability of Floyd¿s algorithm is presented. Finally a model evaluation which demonstrate the correlation between the theoretical analysis and the experimental results is showed.This work has been partially supported by the Spanish Ministry of Education and Science under the contracts TIN2007-68023-C02-01, TIN2007-67188 and CSD2007-00050, by the HiPEAC European Network of Excellence as well as by the Cajal Blue Brain project.Arquitectura de Computadores y Ciencias de la Computación e Inteligencia ArtificialJ. Vigo - Aguiar201120112010info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10115/4691reponame:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlosinstname:Universidad Rey Juan CarlosInglésinfo:eu-repo/semantics/openAccessoai:burjcdigital.urjc.es:10115/46912026-06-24T12:48:17Z
dc.title.none.fl_str_mv H-Isoefficiency: Scalability Metric for Heterogeneous Systems
title H-Isoefficiency: Scalability Metric for Heterogeneous Systems
spellingShingle H-Isoefficiency: Scalability Metric for Heterogeneous Systems
Bosque, Jose Luis
Informática
1203.02 Lenguajes Algorítmicos
title_short H-Isoefficiency: Scalability Metric for Heterogeneous Systems
title_full H-Isoefficiency: Scalability Metric for Heterogeneous Systems
title_fullStr H-Isoefficiency: Scalability Metric for Heterogeneous Systems
title_full_unstemmed H-Isoefficiency: Scalability Metric for Heterogeneous Systems
title_sort H-Isoefficiency: Scalability Metric for Heterogeneous Systems
dc.creator.none.fl_str_mv Bosque, Jose Luis
Robles, Oscar D.
Toharia, Pablo
Pastor, Luis
author Bosque, Jose Luis
author_facet Bosque, Jose Luis
Robles, Oscar D.
Toharia, Pablo
Pastor, Luis
author_role author
author2 Robles, Oscar D.
Toharia, Pablo
Pastor, Luis
author2_role author
author
author
dc.subject.none.fl_str_mv Informática
1203.02 Lenguajes Algorítmicos
topic Informática
1203.02 Lenguajes Algorítmicos
description Scalability is one of the most important features in exascale computing. Most of this systems are heterogeneous and therefore it becomes necessary to develop models and metrics that take into account this heterogeneity. This paper presents a new expression of the isoefficiency function called H-isoefficiency. This function can be applied for both homogeneous and heterogeneous systems and allows to analyze the scalability of a parallel system. Then, as an example, a theoretical a priori analysis of the scalability of Floyd¿s algorithm is presented. Finally a model evaluation which demonstrate the correlation between the theoretical analysis and the experimental results is showed.
publishDate 2010
dc.date.none.fl_str_mv 2010
2011
2011
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10115/4691
url http://hdl.handle.net/10115/4691
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv J. Vigo - Aguiar
publisher.none.fl_str_mv J. Vigo - Aguiar
dc.source.none.fl_str_mv reponame:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
instname:Universidad Rey Juan Carlos
instname_str Universidad Rey Juan Carlos
reponame_str BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
collection BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403972749492224
score 15,811543

Registos relacionados