Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal

Autores
Costanzo, Manuel; Rucci, Enzo; Costi, Ulises; Chichizola, Franco; Naiouf, Marcelo
Año de publicación
2020
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Today, one of the main challenges for high-performance computing systems is to improve their performance by keeping energy consumption at acceptable levels. In this context, a consolidated strategy consists of using accelerators such as GPUs or many-core Intel Xeon Phi processors. In this work, devices of the NVIDIA Pascal and Intel Xeon Phi Knights Landing architectures are described and compared. Selecting the Floyd-Warshall algorithm as a representative case of graph and memory-bound applications, optimized implementations were developed to analyze and compare performance and energy efficiency on both devices. As it was expected, Xeon Phi showed superior when considering double-precision data. However, contrary to what was considered in our preliminary analysis, it was found that the performance and energy efficiency of both devices were comparable using single-precision datatype.
Instituto de Investigación en Informática
Materia
Ciencias Informáticas
Shortest paths
Floyd-Warshall
Xeon Phi
Knights Landing
NVIDIA Pascal
Titan X
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/125518
Acceder
id SEDICI_6039b62141cc024ee7012c193f729b36
oai_identifier_str oai:sedici.unlp.edu.ar:10915/125518
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA PascalCostanzo, ManuelRucci, EnzoCosti, UlisesChichizola, FrancoNaiouf, MarceloCiencias InformáticasShortest pathsFloyd-WarshallXeon PhiKnights LandingNVIDIA PascalTitan XToday, one of the main challenges for high-performance computing systems is to improve their performance by keeping energy consumption at acceptable levels. In this context, a consolidated strategy consists of using accelerators such as GPUs or many-core Intel Xeon Phi processors. In this work, devices of the NVIDIA Pascal and Intel Xeon Phi Knights Landing architectures are described and compared. Selecting the Floyd-Warshall algorithm as a representative case of graph and memory-bound applications, optimized implementations were developed to analyze and compare performance and energy efficiency on both devices. As it was expected, Xeon Phi showed superior when considering double-precision data. However, contrary to what was considered in our preliminary analysis, it was found that the performance and energy efficiency of both devices were comparable using single-precision datatype.Instituto de Investigación en Informática2020-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf37-49http://sedici.unlp.edu.ar/handle/10915/125518enginfo:eu-repo/semantics/altIdentifier/isbn/978-3-030-75836-3info:eu-repo/semantics/altIdentifier/issn/1865-0929info:eu-repo/semantics/altIdentifier/issn/1865-0937info:eu-repo/semantics/altIdentifier/arxiv/2105.07298info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-030-75836-3_3info:eu-repo/semantics/reference/hdl/10915/113268info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T11:29:48Zoai:sedici.unlp.edu.ar:10915/125518Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 11:29:48.513SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
title Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
spellingShingle Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
Costanzo, Manuel
Ciencias Informáticas
Shortest paths
Floyd-Warshall
Xeon Phi
Knights Landing
NVIDIA Pascal
Titan X
title_short Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
title_full Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
title_fullStr Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
title_full_unstemmed Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
title_sort Comparison of HPC Architectures for Computing All-Pairs Shortest Paths: Intel Xeon Phi KNL vs NVIDIA Pascal
dc.creator.none.fl_str_mv Costanzo, Manuel
Rucci, Enzo
Costi, Ulises
Chichizola, Franco
Naiouf, Marcelo
author Costanzo, Manuel
author_facet Costanzo, Manuel
Rucci, Enzo
Costi, Ulises
Chichizola, Franco
Naiouf, Marcelo
author_role author
author2 Rucci, Enzo
Costi, Ulises
Chichizola, Franco
Naiouf, Marcelo
author2_role author
author
author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Shortest paths
Floyd-Warshall
Xeon Phi
Knights Landing
NVIDIA Pascal
Titan X
topic Ciencias Informáticas
Shortest paths
Floyd-Warshall
Xeon Phi
Knights Landing
NVIDIA Pascal
Titan X
dc.description.none.fl_txt_mv Today, one of the main challenges for high-performance computing systems is to improve their performance by keeping energy consumption at acceptable levels. In this context, a consolidated strategy consists of using accelerators such as GPUs or many-core Intel Xeon Phi processors. In this work, devices of the NVIDIA Pascal and Intel Xeon Phi Knights Landing architectures are described and compared. Selecting the Floyd-Warshall algorithm as a representative case of graph and memory-bound applications, optimized implementations were developed to analyze and compare performance and energy efficiency on both devices. As it was expected, Xeon Phi showed superior when considering double-precision data. However, contrary to what was considered in our preliminary analysis, it was found that the performance and energy efficiency of both devices were comparable using single-precision datatype.
Instituto de Investigación en Informática
description Today, one of the main challenges for high-performance computing systems is to improve their performance by keeping energy consumption at acceptable levels. In this context, a consolidated strategy consists of using accelerators such as GPUs or many-core Intel Xeon Phi processors. In this work, devices of the NVIDIA Pascal and Intel Xeon Phi Knights Landing architectures are described and compared. Selecting the Floyd-Warshall algorithm as a representative case of graph and memory-bound applications, optimized implementations were developed to analyze and compare performance and energy efficiency on both devices. As it was expected, Xeon Phi showed superior when considering double-precision data. However, contrary to what was considered in our preliminary analysis, it was found that the performance and energy efficiency of both devices were comparable using single-precision datatype.
publishDate 2020
dc.date.none.fl_str_mv 2020-10
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/125518
url http://sedici.unlp.edu.ar/handle/10915/125518
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/isbn/978-3-030-75836-3
info:eu-repo/semantics/altIdentifier/issn/1865-0929
info:eu-repo/semantics/altIdentifier/issn/1865-0937
info:eu-repo/semantics/altIdentifier/arxiv/2105.07298
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-030-75836-3_3
info:eu-repo/semantics/reference/hdl/10915/113268
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
37-49
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844616177099210752
score 13.069144

Publicaciones similares