Dynamic resource allocation for efficient parallel CFD simulations

CFD users of supercomputers usually resort to rule-of-thumb methods to select the number of subdomains (partitions) when relying on MPI-based parallelization. One common approach is to set a minimum number of elements or cells per subdomain, under which the parallel efficiency of the code is “known”...

Descripción completa

Detalles Bibliográficos
Autores: Houzeaux, Guillaume|||0000-0002-2592-1426, Badia Sala, Rosa Maria|||0000-0003-2941-5499, Borrell Pol, Ricard, Dosimont, Damien, Ejarque Artigas, Jorge, Garcia Gasulla, Marta|||0000-0003-3682-9905, López Herrero, Víctor
Tipo de recurso: artículo
Fecha de publicación:2022
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:2117/369349
Acceso en línea:https://hdl.handle.net/2117/369349
https://dx.doi.org/10.1016/j.compfluid.2022.105577
Access Level:acceso abierto
Palabra clave:Resource allocation
Computational fluid dynamics
Supercomputers
CFD
High performance computing
Elastic computing
Parallel efficiency
MPI
Assignació de recursos
Dinàmica de fluids computacional
Supercomputadors
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
id ES_2aa62c155e8d2dc70b0af73d73fa7e23
oai_identifier_str oai:upcommons.upc.edu:2117/369349
network_acronym_str ES
network_name_str España
repository_id_str
spelling Dynamic resource allocation for efficient parallel CFD simulationsHouzeaux, Guillaume|||0000-0002-2592-1426Badia Sala, Rosa Maria|||0000-0003-2941-5499Borrell Pol, RicardDosimont, DamienEjarque Artigas, JorgeGarcia Gasulla, Marta|||0000-0003-3682-9905López Herrero, VíctorResource allocationComputational fluid dynamicsSupercomputersCFDHigh performance computingElastic computingParallel efficiencyMPICFDAssignació de recursosDinàmica de fluids computacionalSupercomputadorsÀrees temàtiques de la UPC::Informàtica::Arquitectura de computadorsCFD users of supercomputers usually resort to rule-of-thumb methods to select the number of subdomains (partitions) when relying on MPI-based parallelization. One common approach is to set a minimum number of elements or cells per subdomain, under which the parallel efficiency of the code is “known” to fall below a subjective level, say 80%. The situation is even worse when the user is not aware of the “good” practices for the given code and a huge amount of resources can thus be wasted. This work presents an elastic computing methodology that adapts at runtime the resources allocated to a simulation automatically. The criterion to control the required resources is based on a runtime measure of the communication efficiency of the execution. According to some analytical estimates, the resources are then expanded or reduced to fulfill this criterion and eventually execute an efficient simulation.This work has been supported by the Spanish Government (PID2019- 107255GB); by Generalitat de Catalunya (contract 2014-SGR-1051); by the European Commission H2020 project POP CoE (GA n. 824080); by the European Commission H2020 project CompBioMed CoE (GA n. 823712) and by the European Commission and the EuroHPC JU under contract 955558 (eFlows4HPC project).Peer ReviewedElsevier20222022-09-1520222022-06-30journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/369349https://dx.doi.org/10.1016/j.compfluid.2022.105577reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengAgencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2019-107255GB-C21 BSC - COMPUTACION DE ALTAS PRESTACIONES VIIIEuropean Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 824080 Performance Optimisation and Productivity 2European Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 823712 A Centre of Excellence in Computational BiomedicineEuropean Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 955558 Enabling dynamic and Intelligent workflows in the future EuroHPCecosystemopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3693492026-05-27T15:37:01Z
dc.title.none.fl_str_mv Dynamic resource allocation for efficient parallel CFD simulations
title Dynamic resource allocation for efficient parallel CFD simulations
spellingShingle Dynamic resource allocation for efficient parallel CFD simulations
Houzeaux, Guillaume|||0000-0002-2592-1426
Resource allocation
Computational fluid dynamics
Supercomputers
CFD
High performance computing
Elastic computing
Parallel efficiency
MPI
CFD
Assignació de recursos
Dinàmica de fluids computacional
Supercomputadors
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
title_short Dynamic resource allocation for efficient parallel CFD simulations
title_full Dynamic resource allocation for efficient parallel CFD simulations
title_fullStr Dynamic resource allocation for efficient parallel CFD simulations
title_full_unstemmed Dynamic resource allocation for efficient parallel CFD simulations
title_sort Dynamic resource allocation for efficient parallel CFD simulations
dc.creator.none.fl_str_mv Houzeaux, Guillaume|||0000-0002-2592-1426
Badia Sala, Rosa Maria|||0000-0003-2941-5499
Borrell Pol, Ricard
Dosimont, Damien
Ejarque Artigas, Jorge
Garcia Gasulla, Marta|||0000-0003-3682-9905
López Herrero, Víctor
author Houzeaux, Guillaume|||0000-0002-2592-1426
author_facet Houzeaux, Guillaume|||0000-0002-2592-1426
Badia Sala, Rosa Maria|||0000-0003-2941-5499
Borrell Pol, Ricard
Dosimont, Damien
Ejarque Artigas, Jorge
Garcia Gasulla, Marta|||0000-0003-3682-9905
López Herrero, Víctor
author_role author
author2 Badia Sala, Rosa Maria|||0000-0003-2941-5499
Borrell Pol, Ricard
Dosimont, Damien
Ejarque Artigas, Jorge
Garcia Gasulla, Marta|||0000-0003-3682-9905
López Herrero, Víctor
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Resource allocation
Computational fluid dynamics
Supercomputers
CFD
High performance computing
Elastic computing
Parallel efficiency
MPI
CFD
Assignació de recursos
Dinàmica de fluids computacional
Supercomputadors
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
topic Resource allocation
Computational fluid dynamics
Supercomputers
CFD
High performance computing
Elastic computing
Parallel efficiency
MPI
CFD
Assignació de recursos
Dinàmica de fluids computacional
Supercomputadors
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
description CFD users of supercomputers usually resort to rule-of-thumb methods to select the number of subdomains (partitions) when relying on MPI-based parallelization. One common approach is to set a minimum number of elements or cells per subdomain, under which the parallel efficiency of the code is “known” to fall below a subjective level, say 80%. The situation is even worse when the user is not aware of the “good” practices for the given code and a huge amount of resources can thus be wasted. This work presents an elastic computing methodology that adapts at runtime the resources allocated to a simulation automatically. The criterion to control the required resources is based on a runtime measure of the communication efficiency of the execution. According to some analytical estimates, the resources are then expanded or reduced to fulfill this criterion and eventually execute an efficient simulation.
publishDate 2022
dc.date.none.fl_str_mv 2022
2022-09-15
2022
2022-06-30
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/2117/369349
https://dx.doi.org/10.1016/j.compfluid.2022.105577
url https://hdl.handle.net/2117/369349
https://dx.doi.org/10.1016/j.compfluid.2022.105577
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://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2019-107255GB-C21 BSC - COMPUTACION DE ALTAS PRESTACIONES VIII
European Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 824080 Performance Optimisation and Productivity 2
European Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 823712 A Centre of Excellence in Computational Biomedicine
European Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 955558 Enabling dynamic and Intelligent workflows in the future EuroHPCecosystem
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://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-NoDerivatives 4.0 International
http://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_ 1869405085776216065
score 15,300719

Similares en LA Referencia