LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers

Multicore NUMA systems present on-board memory hierarchies and communication networks that influence performance when executing shared memory parallel codes. Characterizing this influence is complex, and understanding the effect of particular hardware configurations on different codes is of paramoun...

ver descrição completa

Detalhes bibliográficos
Autores: Laso Rodríguez, Rubén, García Lorenzo, Óscar, Fernández Rivera, Francisco, Cabaleiro Domínguez, José Carlos, Fernández Pena, Anselmo Tomás, Lorenzo del Castillo, Juan Ángel
Formato: artículo
Fecha de publicación:2021
País:España
Recursos:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:minerva.usc.gal:10347/38988
Acesso em linha:https://hdl.handle.net/10347/38988
Access Level:acceso abierto
Palavra-chave:Hardware counters
Performance
Roofline model
Thread migration
id ES_d9f29792d3bcf192fd0fdf61eba2a5e2
oai_identifier_str oai:minerva.usc.gal:10347/38988
network_acronym_str ES
network_name_str España
repository_id_str
spelling LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing serversLaso Rodríguez, RubénGarcía Lorenzo, ÓscarFernández Rivera, FranciscoCabaleiro Domínguez, José CarlosFernández Pena, Anselmo TomásLorenzo del Castillo, Juan ÁngelHardware countersPerformanceRoofline modelThread migrationMulticore NUMA systems present on-board memory hierarchies and communication networks that influence performance when executing shared memory parallel codes. Characterizing this influence is complex, and understanding the effect of particular hardware configurations on different codes is of paramount importance. In this article, monitoring information extracted from hardware counters at runtime is used to characterize the behavior of each thread for an arbitrary number of multithreaded processes running in a multiprocessing environment. This characterization is given in terms of number of operations per second, operational intensity, and latency of memory accesses. We propose a runtime tool, executed in user space, that uses this information to guide two different thread migration strategies for improving execution efficiency by increasing locality and affinity without requiring any modification in the running codes. Different configurations of NAS Parallel OpenMP benchmarks running concurrently on multicore NUMA systems were used to validate the benefits of our proposal, in which up to four processes are running simultaneously. In more than the 95% of the executions of our tool, results outperform those of the operating system (OS) and produces up to 38% improvement in execution time over the OS for heterogeneous workloads, under different and realistic locality and affinity scenarios.WileyUniversidade de Santiago de Compostela. Departamento de Electrónica e ComputaciónUniversidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)20212021-01-0120212021-01-01journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10347/38988reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostelainstname:Universidad de Santiago de Compostela (USC)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2019-104834GB-I00 COMPUTACION DE ALTAS PRESTACIONES Y CLOUD PARA APLICACIONES DE ALTO INTERESopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:minerva.usc.gal:10347/389882026-06-15T12:47:27Z
dc.title.none.fl_str_mv LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
title LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
spellingShingle LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
Laso Rodríguez, Rubén
Hardware counters
Performance
Roofline model
Thread migration
title_short LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
title_full LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
title_fullStr LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
title_full_unstemmed LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
title_sort LBMA and IMAR2: Weighted lottery based migration strategies for NUMA multiprocessing servers
dc.creator.none.fl_str_mv Laso Rodríguez, Rubén
García Lorenzo, Óscar
Fernández Rivera, Francisco
Cabaleiro Domínguez, José Carlos
Fernández Pena, Anselmo Tomás
Lorenzo del Castillo, Juan Ángel
author Laso Rodríguez, Rubén
author_facet Laso Rodríguez, Rubén
García Lorenzo, Óscar
Fernández Rivera, Francisco
Cabaleiro Domínguez, José Carlos
Fernández Pena, Anselmo Tomás
Lorenzo del Castillo, Juan Ángel
author_role author
author2 García Lorenzo, Óscar
Fernández Rivera, Francisco
Cabaleiro Domínguez, José Carlos
Fernández Pena, Anselmo Tomás
Lorenzo del Castillo, Juan Ángel
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade de Santiago de Compostela. Departamento de Electrónica e Computación
Universidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)
dc.subject.none.fl_str_mv Hardware counters
Performance
Roofline model
Thread migration
topic Hardware counters
Performance
Roofline model
Thread migration
description Multicore NUMA systems present on-board memory hierarchies and communication networks that influence performance when executing shared memory parallel codes. Characterizing this influence is complex, and understanding the effect of particular hardware configurations on different codes is of paramount importance. In this article, monitoring information extracted from hardware counters at runtime is used to characterize the behavior of each thread for an arbitrary number of multithreaded processes running in a multiprocessing environment. This characterization is given in terms of number of operations per second, operational intensity, and latency of memory accesses. We propose a runtime tool, executed in user space, that uses this information to guide two different thread migration strategies for improving execution efficiency by increasing locality and affinity without requiring any modification in the running codes. Different configurations of NAS Parallel OpenMP benchmarks running concurrently on multicore NUMA systems were used to validate the benefits of our proposal, in which up to four processes are running simultaneously. In more than the 95% of the executions of our tool, results outperform those of the operating system (OS) and produces up to 38% improvement in execution time over the OS for heterogeneous workloads, under different and realistic locality and affinity scenarios.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-01-01
2021
2021-01-01
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/10347/38988
url https://hdl.handle.net/10347/38988
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2019-104834GB-I00 COMPUTACION DE ALTAS PRESTACIONES Y CLOUD PARA APLICACIONES DE ALTO INTERES
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
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
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Wiley
publisher.none.fl_str_mv Wiley
dc.source.none.fl_str_mv reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
instname:Universidad de Santiago de Compostela (USC)
instname_str Universidad de Santiago de Compostela (USC)
reponame_str Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
collection Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869421483062722560
score 15.81155

Registos relacionados