A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence

Autores
Mininni, Pablo Daniel; Rosenberg, Duane; Reddy, Raghu; Pouquet, Annick
Año de publicación
2011
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
A hybrid scheme that utilizes MPI for distributed memory parallelism and OpenMP for shared memory parallelism is presented. The work is motivated by the desire to achieve exceptionally high Reynolds numbers in pseudospectral computations of fluid turbulence on emerging petascale, high core-count, massively parallel processing systems. The hybrid implementation derives from and augments a well-tested scalable MPI-parallelized pseudospectral code. The hybrid paradigm leads to a new picture for the domain decomposition of the pseudospectral grids, which is helpful in understanding, among other things, the 3D transpose of the global data that is necessary for the parallel fast Fourier transforms that are the central component of the numerical discretizations. Details of the hybrid implementation are provided, and performance tests illustrate the utility of the method. It is shown that the hybrid scheme achieves good scalability up to ∼20,000 compute cores with a maximum efficiency of 89%, and a mean of 79%. Data are presented that help guide the choice of the optimal number of MPI tasks and OpenMP threads in order to maximize code performance on two different platforms. © 2011 Elsevier B.V. All rights reserved.
Fil: Mininni, Pablo Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina. National Center for Atmospheric Research; Estados Unidos
Fil: Rosenberg, Duane. National Center for Atmospheric Research; Estados Unidos
Fil: Reddy, Raghu. Pittsburgh Supercomputing Center; Estados Unidos
Fil: Pouquet, Annick. National Center for Atmospheric Research; Estados Unidos
Materia
Computational Fluids
Mpi
Numerical Simulation
Openmp
Parallel Scalability
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/56975
Acceder
id CONICETDig_b01e88ffeaa0dc3f28f2312d8813a9b7
oai_identifier_str oai:ri.conicet.gov.ar:11336/56975
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulenceMininni, Pablo DanielRosenberg, DuaneReddy, RaghuPouquet, AnnickComputational FluidsMpiNumerical SimulationOpenmpParallel Scalabilityhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1https://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1A hybrid scheme that utilizes MPI for distributed memory parallelism and OpenMP for shared memory parallelism is presented. The work is motivated by the desire to achieve exceptionally high Reynolds numbers in pseudospectral computations of fluid turbulence on emerging petascale, high core-count, massively parallel processing systems. The hybrid implementation derives from and augments a well-tested scalable MPI-parallelized pseudospectral code. The hybrid paradigm leads to a new picture for the domain decomposition of the pseudospectral grids, which is helpful in understanding, among other things, the 3D transpose of the global data that is necessary for the parallel fast Fourier transforms that are the central component of the numerical discretizations. Details of the hybrid implementation are provided, and performance tests illustrate the utility of the method. It is shown that the hybrid scheme achieves good scalability up to ∼20,000 compute cores with a maximum efficiency of 89%, and a mean of 79%. Data are presented that help guide the choice of the optimal number of MPI tasks and OpenMP threads in order to maximize code performance on two different platforms. © 2011 Elsevier B.V. All rights reserved.Fil: Mininni, Pablo Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina. National Center for Atmospheric Research; Estados UnidosFil: Rosenberg, Duane. National Center for Atmospheric Research; Estados UnidosFil: Reddy, Raghu. Pittsburgh Supercomputing Center; Estados UnidosFil: Pouquet, Annick. National Center for Atmospheric Research; Estados UnidosElsevier Science2011-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/56975Mininni, Pablo Daniel; Rosenberg, Duane; Reddy, Raghu; Pouquet, Annick; A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence; Elsevier Science; Parallel Computing; 37; 6-7; 6-2011; 316-3260167-8191CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.parco.2011.05.004info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S0167819111000512info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:07:10Zoai:ri.conicet.gov.ar:11336/56975instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:07:10.602CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
title A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
spellingShingle A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
Mininni, Pablo Daniel
Computational Fluids
Mpi
Numerical Simulation
Openmp
Parallel Scalability
title_short A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
title_full A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
title_fullStr A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
title_full_unstemmed A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
title_sort A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence
dc.creator.none.fl_str_mv Mininni, Pablo Daniel
Rosenberg, Duane
Reddy, Raghu
Pouquet, Annick
author Mininni, Pablo Daniel
author_facet Mininni, Pablo Daniel
Rosenberg, Duane
Reddy, Raghu
Pouquet, Annick
author_role author
author2 Rosenberg, Duane
Reddy, Raghu
Pouquet, Annick
author2_role author
author
author
dc.subject.none.fl_str_mv Computational Fluids
Mpi
Numerical Simulation
Openmp
Parallel Scalability
topic Computational Fluids
Mpi
Numerical Simulation
Openmp
Parallel Scalability
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv A hybrid scheme that utilizes MPI for distributed memory parallelism and OpenMP for shared memory parallelism is presented. The work is motivated by the desire to achieve exceptionally high Reynolds numbers in pseudospectral computations of fluid turbulence on emerging petascale, high core-count, massively parallel processing systems. The hybrid implementation derives from and augments a well-tested scalable MPI-parallelized pseudospectral code. The hybrid paradigm leads to a new picture for the domain decomposition of the pseudospectral grids, which is helpful in understanding, among other things, the 3D transpose of the global data that is necessary for the parallel fast Fourier transforms that are the central component of the numerical discretizations. Details of the hybrid implementation are provided, and performance tests illustrate the utility of the method. It is shown that the hybrid scheme achieves good scalability up to ∼20,000 compute cores with a maximum efficiency of 89%, and a mean of 79%. Data are presented that help guide the choice of the optimal number of MPI tasks and OpenMP threads in order to maximize code performance on two different platforms. © 2011 Elsevier B.V. All rights reserved.
Fil: Mininni, Pablo Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina. National Center for Atmospheric Research; Estados Unidos
Fil: Rosenberg, Duane. National Center for Atmospheric Research; Estados Unidos
Fil: Reddy, Raghu. Pittsburgh Supercomputing Center; Estados Unidos
Fil: Pouquet, Annick. National Center for Atmospheric Research; Estados Unidos
description A hybrid scheme that utilizes MPI for distributed memory parallelism and OpenMP for shared memory parallelism is presented. The work is motivated by the desire to achieve exceptionally high Reynolds numbers in pseudospectral computations of fluid turbulence on emerging petascale, high core-count, massively parallel processing systems. The hybrid implementation derives from and augments a well-tested scalable MPI-parallelized pseudospectral code. The hybrid paradigm leads to a new picture for the domain decomposition of the pseudospectral grids, which is helpful in understanding, among other things, the 3D transpose of the global data that is necessary for the parallel fast Fourier transforms that are the central component of the numerical discretizations. Details of the hybrid implementation are provided, and performance tests illustrate the utility of the method. It is shown that the hybrid scheme achieves good scalability up to ∼20,000 compute cores with a maximum efficiency of 89%, and a mean of 79%. Data are presented that help guide the choice of the optimal number of MPI tasks and OpenMP threads in order to maximize code performance on two different platforms. © 2011 Elsevier B.V. All rights reserved.
publishDate 2011
dc.date.none.fl_str_mv 2011-06
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/56975
Mininni, Pablo Daniel; Rosenberg, Duane; Reddy, Raghu; Pouquet, Annick; A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence; Elsevier Science; Parallel Computing; 37; 6-7; 6-2011; 316-326
0167-8191
CONICET Digital
CONICET
url http://hdl.handle.net/11336/56975
identifier_str_mv Mininni, Pablo Daniel; Rosenberg, Duane; Reddy, Raghu; Pouquet, Annick; A hybrid MPI-OpenMP scheme for scalable parallel pseudospectral computations for fluid turbulence; Elsevier Science; Parallel Computing; 37; 6-7; 6-2011; 316-326
0167-8191
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1016/j.parco.2011.05.004
info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S0167819111000512
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier Science
publisher.none.fl_str_mv Elsevier Science
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613928310538240
score 13.069144

Publicaciones similares