Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration

The work in this paper focuses on providing malleability to MPI applications by using a novel performance-aware dynamic reconfiguration technique. This paper describes the design and implementation of Flex-MPI, an MPI library extension which can automatically monitor and predict the performance of a...

Descripción completa

Detalles Bibliográficos
Autores: Martín, Gonzalo, Singh, David E., Marinescu, Maria-Cristina, Carretero, Jesús
Tipo de recurso: artículo
Fecha de publicación:2015
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/86919
Acceso en línea:https://hdl.handle.net/2117/86919
https://dx.doi.org/10.1016/j.parco.2015.04.003
Access Level:acceso abierto
Palabra clave:Distributed computing
Distributed systems
Malleable MPI applications
Performance-aware dynamic Reconfiguration
Computational prediction model
High performance computing
Computació distribuïda
Àrees temàtiques de la UPC::Enginyeria electrònica
id ES_31e3a8fbac5005b0b30601acf2320fe3
oai_identifier_str oai:upcommons.upc.edu:2117/86919
network_acronym_str ES
network_name_str España
repository_id_str
spelling Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfigurationMartín, GonzaloSingh, David E.Marinescu, Maria-CristinaCarretero, JesúsDistributed computingDistributed systemsMalleable MPI applicationsPerformance-aware dynamic ReconfigurationComputational prediction modelDistributed systemsHigh performance computingComputació distribuïdaÀrees temàtiques de la UPC::Enginyeria electrònicaThe work in this paper focuses on providing malleability to MPI applications by using a novel performance-aware dynamic reconfiguration technique. This paper describes the design and implementation of Flex-MPI, an MPI library extension which can automatically monitor and predict the performance of applications, balance and redistribute the workload, and reconfigure the application at runtime by changing the number of processes. Unlike existent approaches, our reconfiguring policy is guided by user-defined performance criteria. We focus on iterative SPMD programs, a class of applications with critical mass within the scientific community. Extensive experiments show that Flex-MPI can improve the performance, parallel efficiency, and cost-efficiency of MPI programs with a minimal effort from the programmer.This work has been partially supported by the Spanish Ministry of Economy and Competitiveness under the project TIN2013- 41350-P, Scalable Data Management Techniques for High-End Computing Systems, and EU under the COST Program Action IC1305, Network for Sustainable Ultrascale Computing (NESUS)Peer ReviewedElsevier20152015-07-0120162016-05-11journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/86919https://dx.doi.org/10.1016/j.parco.2015.04.003reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengMinisterio de Economía y Competitividad http://doi.org/10.13039/501100003329 TIN2013-41350-P TECNICAS DE GESTION ESCALABLE DE DATOS PARA HIGH-END COMPUTING SYSTEMSopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivs 4.0 International Licensehttps://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/869192026-05-27T15:37:01Z
dc.title.none.fl_str_mv Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
title Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
spellingShingle Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
Martín, Gonzalo
Distributed computing
Distributed systems
Malleable MPI applications
Performance-aware dynamic Reconfiguration
Computational prediction model
Distributed systems
High performance computing
Computació distribuïda
Àrees temàtiques de la UPC::Enginyeria electrònica
title_short Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
title_full Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
title_fullStr Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
title_full_unstemmed Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
title_sort Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration
dc.creator.none.fl_str_mv Martín, Gonzalo
Singh, David E.
Marinescu, Maria-Cristina
Carretero, Jesús
author Martín, Gonzalo
author_facet Martín, Gonzalo
Singh, David E.
Marinescu, Maria-Cristina
Carretero, Jesús
author_role author
author2 Singh, David E.
Marinescu, Maria-Cristina
Carretero, Jesús
author2_role author
author
author
dc.subject.none.fl_str_mv Distributed computing
Distributed systems
Malleable MPI applications
Performance-aware dynamic Reconfiguration
Computational prediction model
Distributed systems
High performance computing
Computació distribuïda
Àrees temàtiques de la UPC::Enginyeria electrònica
topic Distributed computing
Distributed systems
Malleable MPI applications
Performance-aware dynamic Reconfiguration
Computational prediction model
Distributed systems
High performance computing
Computació distribuïda
Àrees temàtiques de la UPC::Enginyeria electrònica
description The work in this paper focuses on providing malleability to MPI applications by using a novel performance-aware dynamic reconfiguration technique. This paper describes the design and implementation of Flex-MPI, an MPI library extension which can automatically monitor and predict the performance of applications, balance and redistribute the workload, and reconfigure the application at runtime by changing the number of processes. Unlike existent approaches, our reconfiguring policy is guided by user-defined performance criteria. We focus on iterative SPMD programs, a class of applications with critical mass within the scientific community. Extensive experiments show that Flex-MPI can improve the performance, parallel efficiency, and cost-efficiency of MPI programs with a minimal effort from the programmer.
publishDate 2015
dc.date.none.fl_str_mv 2015
2015-07-01
2016
2016-05-11
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/86919
https://dx.doi.org/10.1016/j.parco.2015.04.003
url https://hdl.handle.net/2117/86919
https://dx.doi.org/10.1016/j.parco.2015.04.003
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad http://doi.org/10.13039/501100003329 TIN2013-41350-P TECNICAS DE GESTION ESCALABLE DE DATOS PARA HIGH-END COMPUTING SYSTEMS
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 4.0 International License
https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 4.0 International License
https://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405639922417664
score 15.301603

Similares en LA Referencia